128 accepted papers
Text-to-Image (T2I) models generate high-quality images but are vulnerable to malicious backdoor attacks that inject harmful biases (e.g., trigger-activated gender or racial stereotypes). Existing debiasing methods, often designed for natural statistical biases, struggle with these deliberate and su
How far are deep models from real-world video anomaly understanding (VAU)? Current works typically emphasize detecting unexpected occurrences deviating from normal patterns or comprehending anomalous events with interpretable descriptions. However, they exhibit only a superficial comprehension of re
Recent advances in large language models (LLMs) have shown remarkable capabilities across textual and multimodal domains. In parallel, large language diffusion models have emerged as a promising alternative to the autoregressive paradigm, offering improved controllability, bidirectional context mode
Dynamic Data selection aims to accelerate training by prioritizing informative samples during online training. However, existing methods typically rely on task-specific handcrafted metrics or static/snapshot-based criteria to estimate sample importance, limiting scalability across learning paradigms…
Personalized multi-subject video generation is a promising direction within the field of controllable video generation; however, existing methods face challenges in maintaining cross-frame identity consistency and incur high computational overhead. To address these issues, we propose DiasR, an effic…
The evolution of Large Language Model (LLM) agents towards System~2 reasoning, characterized by deliberative, high-precision problem-solving, necessitates maintaining rigorous logical integrity over extended horizons. However, prevalent memory preprocessing paradigms incur destructive de-contextuali…
Electroencephalography foundation models (EEG-FMs) have advanced brain signal analysis, but the lack of standardized evaluation benchmarks impedes model comparison and scientific progress. Current evaluations rely on inconsistent protocols that render cross-model comparisons unreliable, while a lack…
The remarkable realism of images generated by diffusion models poses critical detection challenges. Current methods utilize reconstruction error as a discriminative feature, exploiting the observation that real images exhibit higher reconstruction errors when processed through diffusion models. Howe
Recent advancements in text-to-image (T2I) generation have led to the emergence of highly expressive models such as diffusion transformers (DiTs), exemplified by FLUX. However, their massive parameter sizes lead to slow inference, high memory usage, and poor deployability. Existing acceleration meth
This paper investigates position control and force estimation for a hydraulic folded pouch actuator. First, experimental platforms are designed to characterize the actuator and the results show two key properties: (i) angular hysteresis when the motion direction reverses, and (ii) strong nonlinearit…
Vision-Language Models (VLMs) are increasingly deployed as autonomous agents to navigate mobile Graphical User Interfaces (GUIs). However, their operation within dynamic on-device ecosystems, which include notifications, pop-ups, and inter-app interactions, exposes them to a unique and underexplored…
Efficient deployment of deep neural networks increasingly relies on Post-Training Quantization (PTQ). Logarithmic PTQ, in particular, promises multiplier-free hardware efficiency, but its performance is often limited by the nonlinear and symmetric quantization grid and standard rounding-to-nearest (…
Cloud removal (CR) in remote sensing imagery is a critical yet challenging task due to complex cloud patterns and diverse underlying ground structures. Despite recent progress in generative models such as diffusion models, CR remains limited by their inadequate capability to perceive and reconstruct
Swarm intelligence for uncrewed aerial vehicles (UAVs) significantly improves the success rate of executing intricate tasks using “distributed platforms and aggregated effects”. However, the high experimental costs and safety risks constrain its development. This paper introduces SIGMA (Swarm Intell…
Low-bit quantization has achieved significant progress in image super-resolution. However, existing quantization methods show evident limitations in handling the heterogeneity of different components. Particularly under extreme low-bit compression, the issue of information loss becomes especially pr…
Decoding visual features from EEG signals is a central challenge in neuroscience, with cross-modal alignment as the dominant approach. We argue that the relationship between visual and brain modalities is fundamentally asymmetric, characterized by two critical gaps: a Fidelity Gap (stemming from EEG
Video Class-Incremental Learning (VCIL) seeks to develop models that continuously learn new action categories over time without forgetting previously acquired knowledge. Unlike traditional Class-Incremental Learning (CIL), VCIL introduces the added complexity of spatiotemporal structures, making it…
Real-time whole-body teleoperation is a critical method for humanoid robots to perform complex tasks in unstructured environments. However, developing a unified controller that robustly supports diverse human motions remains a significant challenge. Existing methods typically distill multiple expert…
Large language model (LLM) services now answer billions of queries per day, and industry reports show that inference, not training, accounts for more than 90% of total power consumption. However, existing benchmarks focus on either training/fine-tuning or performance of inference and provide little
The scarcity of large-scale, open-source data for dialects severely hinders progress in speech technology, a challenge particularly acute for the widely spoken Sichuanese dialects of Chinese. To address this critical gap, we introduce WenetSpeech-Chuan, a 10,000-hour, richly annotated corpus constru…
The development of speech understanding and generation has been significantly accelerated by the availability of large-scale, high-quality speech datasets. Among these, ASR and TTS are regarded as the most established and fundamental tasks. However, for Cantonese (Yue Chinese), spoken by approximate
As massive MIMO and extremely large antenna array rapidly evolve, wireless communication is gradually shifting from the far-field to the near-field region. To accurately capture the characteristics of the near-field channel, the spherical-wave assumption has to be applied, making channel estimation…
Unmanned aerial vehicle (UAV) swarms find extensive applications in diverse fields, including search and rescue, logistics delivery, and environmental surveillance, necessitating meticulous task and temporal scheduling to meet intricate spatiotemporal requirements. A market-based strategy emerges as
Unmanned aerial vehicles (UAVs) are critical in the automated inspection of wind turbine blades. Nevertheless, several issues persist in this domain. Firstly, existing inspection platforms encounter challenges in meeting the demands of automated inspection tasks and scenarios. Moreover, current blad
Depth estimation is one of the key technologies for realizing 3D perception in unmanned systems. Monocular depth estimation has been widely researched because of its low-cost advantage, but the existing methods face the challenges of poor depth estimation performance and blurred object boundaries on
Distributed task allocation in the UAV swarm is sensitive to excessive communication overhead and frequent transmissions. Combining reinforcement learning and task allocation demonstrates great potential in enhancing algorithm performance and optimizing communication. However, existing studies rely
Existing works have extensively studied adversarial examples, which are minimal perturbations that can mislead the output of deep neural networks (DNNs) while remaining imperceptible to humans. However, in this work, we reveal the existence of a harmless perturbation space, in which perturbations dr…
Vision-Language Models (VLMs) face two critical limitations in visual representation learning: degraded supervision due to information loss during gradient propagation, and the inherent semantic sparsity of textual supervision compared to visual data. We propose the Diffusion Supervision Vision-Lang…
In this paper, we present a novel approach, termed Double-Filter,to “slim down” the fine-tuning process of vision-language pre-trained (VLP) models via filtering redundancies in feature inputs and architectural components. We enhance the fine-tuning process using two approaches. First, we develop a…
In the field of AI security, deep neural networks (DNNs) are highly sensitive to adversarial examples (AEs), which can cause incorrect predictions with minimal input perturbations. Although AEs exhibit transferability across models, targeted attack success rates (TASRs) are low due to differences in…
Graph Neural Networks (GNNs) achieve strong performance in node classification tasks but exhibit substantial performance degradation under label noise. Despite recent advances in noise-robust learning, a principled approach that exploits the node-neighbor interdependencies inherent in graph data for…
Aerial-Ground person re-identification (AG-ReID) is an emerging yet challenging task that aims to match pedestrian images captured from drastically different viewpoints, typically from unmanned aerial vehicles (UAVs) and ground-based surveillance cameras. The task poses significant challenges due to…
In recent years, the proliferation of renewable energy sources has heightened the focus on networked energy systems. These systems face significant challenges due to the unpredictable nature of energy generation and consumption, as well as the complexity of managing numerous components and parameter…
Text-to-video (T2V) generation has made tremendous progress in generating complicated scenes based on texts. However, human-object interaction (HOI) often cannot be precisely generated by current T2V models due to the lack of large-scale videos with accurate captions for HOI. To address this issue,…
Multi-agent systems can be extremely efficient when working concurrently and collaboratively, e.g., for delivery, surveillance, search and rescue. Coordination of such teams often involves two aspects: (i) selecting appropriate subteams for different tasks in various areas; (ii) coordinating agents
Facial reactions convey crucial emotional information and coordinating interpersonal relationships in human dyadic interactions. While existing Multiple Appropriate Facial Reaction Generation (MAFRG) methods focus on generating multiple reasonable facial reactions, none of these approaches combines…
Image fusion combines images from multiple domains into one image, containing complementary information from source domains. Existing methods take pixel intensity, texture and high-level vision task information as the standards to determine preservation of information, lacking enhancement for human…
Vision-Language Models (VLMs) exhibit impressive performance, yet the integration of powerful vision encoders has significantly broadened their attack surface, rendering them increasingly susceptible to jailbreak attacks. However, lacking well-defined attack objectives, existing jailbreak methods of…
Graph Neural Networks (GNNs) excel in many applications but struggle when trained with noisy labels, especially as noise can propagate through the graph structure. Despite recent progress in developing robust GNNs, few methods exploit the intrinsic properties of graph data to filter out noise. In th
The effectiveness of instruction fine-tuning for Large Language Models is fundamentally constrained by the quality and efficiency of training datasets. This work introduces Low-Confidence Gold (LCG), a novel filtering framework that employs centroid-based clustering and confidence-guided selection f
The challenge of inconsistent modalities in real-world applications presents significant obstacles to effective object re-identification (ReID). However, most existing approaches assume modality-matched conditions, significantly limiting their effectiveness in modality-mismatched scenarios. To overc…
We present MFRNet, a novel network for multi-modal object re-identification that integrates multi-modal data features to effectively retrieve specific objects across different modalities. Current methods suffer from two principal limitations: (1) insufficient interaction between pixel-level semantic…
A reliable communication network is essential for multiple UAVs operating within obstacle-cluttered environments, where limited communication due to obstructions often occurs. A common solution is to deploy intermediate UAVs to relay information via a multi-hop network, which introduces two challeng
Emotion Recognition in Conversation (ERC) aims to detect the emotions of individual utterances within a conversation. Generating efficient and modality-specific representations for each utterance remains a significant challenge. Previous studies have proposed various models to integrate features ext
Non-intrusive speech quality assessment (NISQA) is widely used in speech downstream tasks due to its ability to predict the quality of speech without a reference speech. However, few researchers have focused on the backdoor security of NISQA. Despite the backdoor defenses have been extensively studi…
Generative models have recently gained attention in recommendation systems by directly predicting item identifiers from user interaction sequences. However, existing methods suffer from significant information loss due to the separation of stages such as quantization and sequence modeling, hindering…
The use of denoising diffusion models is becoming increasingly popular in the field of image editing. However, current approaches often rely on either image-guided methods, which provide a visual reference but lack control over semantic consistency, or text-guided methods, which ensure alignment wit…
Distributed learning is commonly used for training deep learning models, especially large models. In distributed learning, manual parallelism (MP) methods demand considerable human effort and have limited flexibility. Hence, automatic parallelism (AP) methods have recently been proposed for automati…
Personalized Federated Learning (pFL) mitigates the impact of statistical heterogeneity on FL architecture to some extent by allowing participants to use personalized models based on local data distributions. The existing pFL methods optimize from the perspective of model structure, attempting to ad…
Interactive 3D generation is gaining momentum and capturing extensive attention for its potential to create immersive virtual experiences. However, a critical challenge in current 3D generation technologies lies in achieving real-time interactivity. To address this issue, we introduce WonderTurbo, t…
In this paper, we explore the joint design of a transmit waveform and receive filter to enhance the detection performance of multiple-input multiple-output (MIMO) radar. Target echoes are assumed to be embedded in signal-dependent interference and colored Gaussian noise. As design metrics, we exploi…
Autonomous driving has traditionally relied heavily on costly and labor-intensive High Definition (HD) maps, hindering scalability. In contrast, Standard Definition (SD) maps are more affordable and have worldwide coverage, offering a scalable alternative. In this work, we systematically explore the…
Regular maintenance and inspection of cables are essential for cable-stayed bridges and suspension bridges, as cables serve as the core components. In order to enable automated detection of cables, this paper proposes a novel wheeled cable inspection robot. The robot utilizes a bilateral wheel struc…
"Face anti-spoofing (FAS) plays a vital role in preventing face recognition (FR) systems from presentation attacks. Nowadays, FAS systems face the challenge of domain shift, impacting the generalization performance of existing FAS methods. In this paper, we rethink about the inherence of domain shif…
The goal-reaching tasks with safety constraints are common control problems in real world, such as intelligent driving and robot manipulation. The difficulty of this kind of problem comes from the exploration termination caused by safety constraints and the sparse rewards caused by goals. The existi…
Transductive node prediction has been a popular learning setting in Graph Neural Networks (GNNs). It has been widely observed that the shortage of information flow between the distant nodes and intra-batch nodes (for large-scale graphs) often hurt the generalization of GNNs which overwhelmingly adop…
One-step Weakly Supervised Person Search (WSPS) jointly performs pedestrian detection and person Re-IDentification (ReID) only with bounding box annotations, which makes the traditional person ReID problem more suitable and efficient for real-world applications. However, this task is very challengin…
The global multi-object tracking (MOT) system can consider interaction, occlusion, and other ``visual blur'' scenarios to ensure effective object tracking in long videos. Among them, graph-based tracking-by-detection paradigms achieve surprising performance. However, their fully-connected nature pos…
In semiconductor manufacturing, to improve the throughput of cluster tools, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">process modules</i> (PMs) are designed to have multiple spaces such that more than one wafers can be processed in a PM concurr
Multi-object tracking (MOT) is a cornerstone capability of any robotic system. Tracking quality is largely dependent on the quality of input detections. In many applications, such as autonomous driving, it is preferable to over-detect objects to avoid catastrophic outcomes due to missed detections.
Safe coordination of fixed-wing UAVs in unstructured environments poses challenges due to the intricate coupling of UAV cooperation, obstacle avoidance, and motion constraints. One task is time-critical coordination, which means that all UAVs can safely reach their destinations simultaneously. Exist
Depth estimation is a cornerstone for autonomous driving, yet acquiring per-pixel depth ground truth for supervised learning is challenging. Self-Supervised Surround Depth Estimation (SSSDE) from consecutive images offers an economical alternative. While previous SSSDE methods have proposed differen…
In reality, multi-object tracking (MOT) is used in a wide range of scenarios. Maintaining the motion trajectory of the target, especially in high-density pedestrian scenarios, is often difficult. The tracking quality of most multi-object trackers correlates strongly with the detector quality and the…
UAV swarms have attracted much attention for post-disaster search and rescue, pollution monitoring and trace-ability, etc., where distributed scheduling is required to arrange careful tasks and time quickly. The market-based methods are widely favored but they rely on the environmentally influenced…
The appearance of an object can be fleeting when it transforms. As eggs are broken or paper is torn, their color, shape, and texture can change dramatically, preserving virtually nothing of the original except for the identity itself. Yet, this important phenomenon is largely absent from existing vi…
A key contributor to recent progress in 3D detection from single images is monocular depth estimation. Existing methods focus on how to leverage depth explicitly, by generating pseudo-pointclouds or providing attention cues for image features. More recent works leverage depth prediction as a pretrai…
While deep learning models have achieved the state-of-the-art performance on single-image rain removal, most methods only consider learning fixed mapping rules on the single synthetic dataset for lifetime. This limits the real-life application as iterative optimization may change mapping rules and t…
Recently, some weakly supervised multi-object tracking (MOT) methods learn identity embedding features with pseudo identity labels rather than the high-cost manual ones. However, these pseudo identity labels may contain many false or missing identities, which adversely affect the optimization of tra…
Visible-infrared person re-identification (VI-ReID), which aims to search identities across different spectra, is a challenging task due to large cross-modality discrepancy between visible and infrared images. The key to reduce the discrepancy is to filter out identity-irrelevant interference and ef…
Building 3D perception systems for autonomous vehicles that do not rely on high-density LiDAR is a critical research problem because of the expense of LiDAR systems compared to cameras and other sensors. Recent research has developed a variety of camera-only methods, where features are differentiabl…
This work proposes an end-to-end multi-camera 3D multi-object tracking (MOT) framework. It emphasizes spatio-temporal continuity and integrates both past and future reasoning for tracked objects. Thus, we name it "Past-and-Future reasoning for Tracking" (PF-Track). Specifically, our method adapts th…
Graph Neural Networks (GNNs) have demonstrated superior performance in numerous real-world applications. Despite their success, recent studies have shown that GNNs are vulnerable under edge inference attacks aimed to infer the connectivity of a given pair of nodes. However, existing methods primaril…
Tracking objects with persistence in cluttered and dynamic environments remains a difficult challenge for computer vision systems. In this paper, we introduce TCOW, a new benchmark and model for visual tracking through heavy occlusion and containment. We set up a task where the goal is to, given a v…
3D object detection from visual sensors is a cornerstone capability of robotic systems. State-of-the-art methods focus on reasoning and decoding object bounding boxes from multi-view camera input. In this work we gain intuition from the integral role of multi-view consistency in 3D scene understandi…
Traffic flow prediction is of particular interest since its massive applications in intelligent transportation systems (ITS). The problem is challenging due to the complex spatio-temporal correlations and nonlinearities of traffic flows. However, existing methods based on the graph neural networks c…
Aiming at the problem that the low-cost Strapdown Inertial Navigation System (SINS)/Global Positioning System (GPS) cannot effectively achieve fast in-flight alignment with short-endurance, an improved alignment method based on backtracking navigation is proposed. Firstly, the existing backtracking
Experienced human drivers always make safe driving decisions by selectively observing the front, rear and side- view mirrors. Several end - to-end methods have been pro-posed to learn driving models with multi-view visual infor-mation. However, these benchmark methods lack semantic understanding of…
"Previous studies have verified that the functionality of black-box models can be stolen with full probability outputs. However, under the more practical hard-label setting, we observe that existing methods suffer from catastrophic performance degradation. We argue this is due to the lack of rich in…
Deep learning models for handwriting recognition have been developed in recent years. To improve the model’s generalization ability for sequence modeling task, this paper proposes to use domain adaptation with statistical distribution alignment and entropy regularization. For statistical distributio…
Recent non-local self-attention methods have proven to be effective in capturing long-range dependencies for semantic segmentation. These methods usually form a similarity map of R^(CxC) (by compressing spatial dimensions) or R^(HWxHW) (by compressing channels) to describe the feature relations alon…
Although randomized smoothing has demonstrated high certified robustness and superior scalability to other certified defenses, the high computational overhead of the robustness certification bottlenecks the practical applicability, as it depends heavily on the large sample approximation for estimati…
Deep generative networks have achieved great success on distorted image restoration. However, existing deep learning approaches mainly focus on delicate module structure while ignoring the saturation problem. In this paper, we study the influence of different learning schemes on fitting capability a…
Transfer adversarial attack is a non-trivial black-box adversarial attack that aims to craft adversarial perturbations on the surrogate model and then apply such perturbations to the victim model. However, the transferability of perturbations from existing methods is still limited, since the adversa…
This paper proposes a self-supervised objective for learning representations that localize objects under occlusion - a property known as object permanence. A central question is the choice of learning signal in cases of total occlusion. Rather than directly supervising the locations of invisible obj…
Bootstrap aggregating (bagging) is an effective ensemble protocol, which is believed can enhance robustness by its majority voting mechanism. Recent works further prove the sample-wise robustness certificates for certain forms of bagging (e.g. partition aggregation). Beyond these particular forms, i…
How to achieve better results with fewer labeling costs remains a challenging task. In this paper, we present a new active learning framework, which for the first time incorporates contrastive learning into recently proposed one-bit supervision. Here one-bit supervision denotes a simple Yes or No qu…
"3D multi-object tracking aims to uniquely and consistently identify all mobile entities through time. Despite the rich spatiotemporal information available in this setting, current 3D tracking methods primarily rely on abstracted information and limited history, e.g. single-frame object bounding bo…
Visual Emotion Analysis (VEA) has attracted increasing attention recently with the prevalence of sharing images on social networks. Since human emotions are ambiguous and subjective, it is more reasonable to address VEA in a label distribution learning (LDL) paradigm rather than a single-label class…
The decision-based black-box attack means to craft adversarial examples with only the top-1 label of the victim model available. A common practice is to start from a large perturbation and then iteratively reduce it with a deterministic direction and a random one while keeping it adversarial. The li…
Lung cancer has been the leading death cause in modern society. Early detection of pulmonary nodules can significantly improve the survival rate of lung cancer. In this paper, we propose a novel pulmonary nodule detection framework and a novel 3D dense attention module (DAM) which can efficiently ex…
The DNS hijacking attack represents a significant threat to users. In this type of attack, a malicious DNS server redirects a victim domain to an attacker-controlled web server. Existing defenses are not scalable and have not been widely deployed. In this work, we propose both unsupervised and semi-…
Artistic style transfer aims at migrating the style from an example image to a content image. Currently, optimization-based methods have achieved great stylization quality, but expensive time cost restricts their practical applications. Meanwhile, feed-forward methods still fail to synthesize comple…
Simulators can efficiently generate large amounts of labeled synthetic data with perfect supervision for hard-to-label tasks like semantic segmentation. However, they introduce a domain gap that severely hurts real-world performance. We propose to use self-supervised monocular depth estimation as a…
Panoptic segmentation brings together two separate tasks: instance and semantic segmentation. Although they are related, unifying them faces an apparent paradox: how to learn simultaneously instance-specific and category-specific (i.e. instance-agnostic) representations jointly. Hence, state-of-the-…
3D semantic scene completion and 2D semantic segmentation are two tightly correlated tasks that are both essential for indoor scene understanding, because they predict the same semantic classes, using positively correlated high-level features. Current methods use 2D features extracted from early-fus…
This paper studies the problem of inverse cloth simulation---to estimate shape and time-varying poses of the underlying body that generates physically plausible cloth motion, which matches to the point cloud measurements on the clothed humans. A key innovation is to represent the dynamics of the clo…
Recent progress in 3D object detection from single images leverages monocular depth estimation as a way to produce 3D pointclouds, turning cameras into pseudo-lidar sensors. These two-stage detectors improve with the accuracy of the intermediate depth estimation network, which can itself be improved…
Tracking by detection, the dominant approach for online multi-object tracking, alternates between localization and association steps. As a result, it strongly depends on the quality of instantaneous observations, often failing when objects are not fully visible. In contrast, tracking in humans is un…
Previous convolutional neural network (CNN) based blind super-resolution (SR) methods usually adopt an iterative optimization way to approximate the ground-truth (GT) step-by-step. This solution always involves more computational costs to bring about time-consuming inference. At present, most blind…
Computer vision tasks such as object detection and semantic/instance segmentation rely on the painstaking annotation of large training datasets. In this paper, we propose LocTex that takes advantage of the low-cost localized textual annotations (i.e., captions and synchronized mouse-over gestures) t…
Voice conversion (VC) is a task to convert the voice of speech while preserving its linguistic content. Although several methods have been proposed to enable VC with non-parallel data, it is still difficult to model the voice without a great number of data or an adaptive process. In this paper, we p…
Multi-object tracking is an important ability for an autonomous vehicle to safely navigate a traffic scene. Current state-of-the-art follows the tracking-by-detection paradigm where existing tracks are associated with detected objects through some distance metric. Key challenges to increase tracking…
To maximize the signal-to-interference-plus-noise ratio (SINR) under a constant-envelope constraint, an efficient joint design of the transmit waveform and the receive filter for multipleinput multiple-output (MIMO) radars is essential. In this paper, we propose a novel optimization framework to sol…
Active suspensions are important features of many recent planetary rovers. For such a rover, the control strategy is crucial to its performance. This letter presents the control method for a planetary rover equipped with an active suspension system. The control algorithm is based on the estimation o
LiDAR point cloud analysis is a core task for 3D computer vision, especially for autonomous driving. However, due to the severe sparsity and noise interference in the single sweep LiDAR point cloud, the accurate semantic segmentation is non-trivial to achieve. In this paper, we propose a novel spars…
As a voxel-wise labeling task, semantic scene completion (SSC) tries to simultaneously infer the occupancy and semantic labels for a scene from a single depth and/or RGB image. The key challenge for SSC is how to effectively take advantage of the 3D context to model various objects or stuffs with se…
Lighter model and faster inference are the focus of current single image super-resolution (SISR) research. However, existing methods are still hard to be applied in real-world applications due to the requirement of its heavy computation. Model quantization is an effective way to significantly reduce…
Real-time scene parsing is a fundamental feature for autonomous driving vehicles with multiple cameras. In this letter we demonstrate that sharing semantics between cameras with different perspectives and overlapping views can boost the parsing performance when compared with traditional methods, whi
Semantic scene completion (SSC) refers to the task of inferring the 3D semantic segmentation of a scene while simultaneously completing the 3D shapes. We propose PALNet, a novel hybrid network for SSC based on single depth. PALNet utilizes a two-stream network to extract both 2D and 3D features from
The extensive computational burden limits the usage of accurate but complex object detectors in resource-bounded scenarios. In this paper, we present a lightweight object detector, named LightDet, to address this dilemma. We design a lightweight backbone that is able to capture rich low-level featur…
In autonomous driving, accurately estimating the state of surrounding obstacles is critical for safe and robust path planning. However, this perception task is difficult, particularly for generic obstacles/objects, due to appearance and occlusion changes. To tackle this problem, we propose an end-to…
Generating adversarial examples in a black-box setting retains a significant challenge with vast practical application prospects. In particular, existing black-box attacks suffer from the need for excessive queries, as it is non-trivial to find an appropriate direction to optimize in the high-dimens…
Panoptic segmentation is a complex full scene parsing task requiring simultaneous instance and semantic segmentation at high resolution. Current state-of-the-art approaches cannot run in real-time, and simplifying these architectures to improve efficiency severely degrades their accuracy. In this pa…
Self-supervised learning is showing great promise for monocular depth estimation, using geometry as the only source of supervision. Depth networks are indeed capable of learning representations that relate visual appearance to 3D properties by implicitly leveraging category-level patterns. In this w…
RGB images differentiate from depth as they carry more details about the color and texture information, which can be utilized as a vital complement to depth for boosting the performance of 3D semantic scene completion (SSC). SSC is composed of 3D shape completion (SC) and semantic scene labeling whi…
Dense depth estimation from a single image is a key problem in computer vision, with exciting applications in a multitude of robotic tasks. Initially viewed as a direct regression problem, requiring annotated labels as supervision at training time, in the past few years a substantial amount of work
Deep Learning for Computer Vision depends mainly on the source of supervision. Photo-realistic simulators can generate large-scale automatically labeled synthetic data, but introduce a domain gap negatively impacting performance. We propose a new unsupervised domain adaptation algorithm, called SPIG…
Attention-based sequence-to-sequence architectures have made great progress in the speech recognition task. The SpeechTransformer, a no-recurrence encoder-decoder architecture, has shown promising results on small-scale speech recognition data sets in previous works. In this paper, we focus on a lar…
Learning depth and camera ego-motion from raw unlabeled RGB video streams is seeing exciting progress through self-supervision from strong geometric cues. To leverage not only appearance but also scene geometry, we propose a novel self-supervised two-stream network using RGB and inferred depth infor
Deep learning models have shown their vulnerabilities to universal adversarial perturbations (UAP), which are quasi-imperceptible. Compared to the conventional supervised UAPs that suffer from the knowledge of training data, the data-independent unsupervised UAPs are more applicable. Existing unsupe…
Universal adversarial perturbations (UAPs), a.k.a. input-agnostic perturbations, has been proved to exist and be able to fool cutting-edge deep learning models on most of the data samples. Existing UAP methods mainly focus on attacking image classification models. Nevertheless, little attention has…
In this paper, we present a multi-camera visual odometry (VO) system for an autonomous vehicle. Our system mainly consists of a virtual LiDAR and a pose tracker. We use a perspective transformation method to synthesize a surroundview image from undistorted fisheye camera images. With a semantic segm…
In this paper, given the speaker bottleneck feature vectors extracted with speaker discriminant neural networks, we focus on using the sequential speaker characteristics for text-dependent speaker verification. In each evaluation trial, speaker supervectors are used as the representations of the seq…
This letter reports on a real-time simultaneous localization and mapping (SLAM) algorithm for an underwater robot using an imaging forward-looking sonar and its application in the area of autonomous underwater ship hull inspection. The proposed algorithm overcomes specific challenges associated with
This letter reports on WaterGAN, a generative adversarial network (GAN) for generating realistic underwater images from in-air image and depth pairings in an unsupervised pipeline used for color correction of monocular underwater images. Cameras onboard autonomous and remotely operated vehicles can
Feature learning has become popular in robotics due to recent advances in machine learning. In this paper, we propose a novel method to utilize the high-dimensional features from these techniques as observations in Bayesian estimation problems in a real-time manner. We develop an approach that: 1) p…
This paper reports on a method to perform robust visual relocalization between temporally separated sets of underwater images gathered by a robot. The place recognition and relocalization problem is more challenging in the underwater environment mainly due to three factors: 1) changes in illuminatio…