73 accepted papers
Adapting vision-language models to remote sensing imagery remains challenging due to two key factors: limited semantic coverage in textual representations and insufficient adaptability of visual features. These issues are particularly significant in aerial scenes, which involve various visual appear
Assistive teleoperation enhances efficiency via shared control, yet inter-operator variability, stemming from diverse habits and expertise, induces highly heterogeneous trajectory distributions that undermine intent recognition stability. We present Adaptor, a few-shot framework for robust cross-ope…
Multi-view automatic translational correction (ATC) in coronary angiography (CAG) is critical for intraoperative automatic diagnosis, in which deep learning playing a key role. However, heartbeat-induced soft matching errors and costly annotations make it difficult to build high-quality, large-scale
Integrating Ordinary Differential Equations (ODEs) with U-shaped neural networks has emerged as a novel direction in medical image segmentation. Current networks predominantly employ discretization methods incorporating ODEs. However, these methods face inherent trade-offs between model compactness,
Video Large Language Models (VLMs) have achieved remarkable success in video understanding, but the significant computational cost from processing dense frames severely limits their practical application. Existing methods alleviate this by selecting keyframes, but their greedy decision-making, combi
Physical adversarial attacks in driving scenarios can expose critical vulnerabilities in visual perception models. However, developing such attacks remains non-trivial due to diverse real-world environmental influences. Existing approaches either struggle to generalize to dynamic environments or fai
Vision–Language Models (VLMs) are increasingly deployed with web search tools, yet we still lack benchmarks that isolate a critical capability for real-world use: deciding when to search and how to steer search from ambiguous visual evidence, especially when multiple images provide overlapping or co…
The inherent differences between spike cameras and traditional frame-based cameras lead to more complex and diverse noise characteristics, particularly under extremely low-light conditions. Existing noise modeling approaches for spike camera predominantly rely on inter-spike intervals (ISI) for nois
Recent advances in text-to-image (T2I) generation via reinforcement learning (RL) have benefited from reward models that assess semantic alignment and visual quality. However, most existing reward models pay limited attention to fine-grained spatial relationships, often producing images that appear
Fragmented image recovery is of significant importance in computer vision, such as cultural relic and artwork restoration, archival document recovery, and digital forensics. The goal is to recover the original image topology from an unordered set of fragments and spatially align and stitch them toge
Despite significant advancements in the research of aquatic-aerial robots, existing configurations struggle to efficiently perform underwater, surface, and aerial movement. In this paper, we propose a novel multimodal surfing aquatic-aerial vehicle, SurfAAV, which efficiently integrates underwater n…
We construct VisualPRM400K, a dataset comprising about 400K multimodal process supervision data. Building upon this dataset, we develop VisualPRM, an advanced multimodal Process Reward Model (PRM) capable of estimating the value score of each step during the reasoning process. Under the Best-of-N ev…
The rapid advancement of Multimodal Large Language Models (MLLMs) has revealed the limitations of existing benchmarks in evaluating complex reasoning over multiple images. To address this gap, we introduce MIRACLE, a novel benchmark for Multi-Image complex Reasoning And Comprehension Logic Evaluatio
Stereo depth estimation is a critical task in autonomous driving and robotics, where inaccuracies (such as misidentifying nearby objects as distant) can lead to dangerous situations. Adversarial attacks against stereo depth estimation can help revealing vulnerabilities before deployment. Previous wo…
Large vision-language models (LVLMs) have shown remarkable capabilities in interpreting visual content. While existing works demonstrate these models' vulnerability to deliberately placed adversarial texts, such texts are often easily identifiable as anomalous. In this paper, we present the first ap…
Despite significant advancements in the research of aquatic-aerial robots, existing configurations struggle to efficiently perform underwater, surface, and aerial movement. In this paper, we propose a novel multimodal surfing aquaticaerial vehicle, SurfAAV, which efficiently integrates underwater na
Large multimodal models demonstrate remarkable generalist ability to perform diverse multimodal tasks in a zero-shot manner. Large-scale web-based image-text pairs contribute fundamentally to this success but suffer from excessive noise. Recent studies use alternative captions synthesized by caption…
Although Federated Learning (FL) enables collaborative model training without sharing the raw data of clients, it encounters low-performance problems caused by various heterogeneous scenarios. Due to the limitation of dispatching the same global model to clients for local training, traditional Feder…
We introduce a novel approach to counter adversarial attacks, namely, image resampling. Image resampling transforms a discrete image into a new one, simulating the process of scene recapturing or rerendering as specified by a geometrical transformation. The underlying rationale behind our idea is th…
Large, high-capacity models trained on diverse datasets have shown remarkable successes on efficiently tackling downstream applications. In domains from NLP to Computer Vision, this has led to a consolidation of pretrained models, with general pretrained backbones serving as a starting point for man
Large, high-capacity models trained on diverse datasets have shown remarkable successes on efficiently tackling downstream applications. In domains from NLP to Computer Vision, this has led to a consolidation of pretrained models, with general pretrained backbones serving as a starting point for man…
Non-rigid point cloud registration remains a significant challenge in 3D computer vision due to the complexity of structural deforms, lack of overlaps, and sensitivity to initialization. This paper introduces a framework inspired by the recent success in recurrent architecture, adapted to accommodat…
Vision transformers (ViT) have shown promise in various vision tasks while the U-Net based on a convolutional neural network (CNN) remains dominant in diffusion models. We design a simple and general ViT-based architecture (named U-ViT) for image generation with diffusion models. U-ViT is characteri…
Motivated by the efficiency and rapid convergence of pre-trained models for solving downstream tasks, this paper extensively studies the impact of Continual Learning (CL) models as pre-trainers. We find that, in both supervised and unsupervised CL, the transfer quality of representations does not sh…
Recent years have witnessed a remarkable success of large deep learning models. However, training these models is challenging due to high computational costs, painfully slow convergence, and overfitting issues. In this paper, we present Deep Incubation, a novel approach that enables the efficient an…
Deep learning has been successfully used to automate the modeling process that trains a network/model from a given experimental dataset to calculate the output directly using high-dimensional complex raw data. However, the trained network is an inverse of the welding process (forward process) that p
We launch EVA, a vision-centric foundation model to explore the limits of visual representation at scale using only publicly accessible data. EVA is a vanilla ViT pre-trained to reconstruct the masked out image-text aligned vision features conditioned on visible image patches. Via this pretext task,…
Point cloud registration (PCR) aims to recover the rigid transformation between two noisy, unordered point sets. This task is typically tackled by establishing point-wise correspondences, and solving the rigid transformation between the two sets. Since descriptor-based methods find correspondences b…
In-context learning, as a new paradigm in NLP, allows the model to rapidly adapt to various tasks with only a handful of prompts and examples. But in computer vision, the difficulties for in-context learning lie in that tasks vary significantly in the output representations, thus it is unclear how t…
CLIP models have demonstrated impressively high zero-shot recognition accuracy, however, their fine-tuning performance on downstream vision tasks is sub-optimal. Contrarily, masked image modeling (MIM) performs exceptionally for fine-tuning on downstream tasks, despite the absence of semantic labels…
It has become a common practice for many perceptual systems to integrate information from multiple sensors to improve the accuracy of object detection. For example, autonomous vehicles use visible light, and infrared (IR) information to ensure that the car can cope with complex weather conditions. H…
Scaling properties have been one of the central issues in self-supervised pre-training, especially the data scalability, which has successfully motivated the large-scale self-supervised pre-trained language models and endowed them with significant modeling capabilities. However, scaling properties s…
This paper proposes a unified diffusion framework (dubbed UniDiffuser) to fit all distributions relevant to a set of multi-modal data in one model. Our key insight is -- learning diffusion models for marginal, conditional, and joint distributions can be unified as predicting the noise in the perturb…
Although deep neural networks have achieved astonishing performance in many vision tasks, existing learning-based methods are far inferior to the physical model-based solutions in extreme low-light sensor noise modeling. To tap the potential of learning-based sensor noise modeling, we investigate th…
Masked image modeling (MIM) as pre-training is shown to be effective for numerous vision downstream tasks, but how and where MIM works remain unclear. In this paper, we compare MIM with the long-dominant supervised pre-trained models from two perspectives, the visualizations and the experiments, to…
A large-scale deep model pre-trained on massive labeled or unlabeled data transfers well to downstream tasks. Linear evaluation freezes parameters in the pre-trained model and trains a linear classifier separately, which is efficient and attractive for transfer. However, little work has investigated…
We present SegGPT, a generalist model for segmenting everything in context. We unify various segmentation tasks into a generalist in-context learning framework that accommodates different kinds of segmentation data by transforming them into the same format of images. The training of SegGPT is formul…
This paper presents a method that effectively combines two prevalent visual recognition methods, i.e., image classification and contrastive language-image pre-training, dubbed iCLIP. Instead of naive multi-task learning that use two separate heads for each task, we fuse the two tasks in a deep fashi…
"Current object detection systems and benchmarks typically handle a limited number of categories, up to about a thousand categories. This paper scales the number of categories for object detection systems and benchmarks up to 21,000, by leveraging existing object detection and image classification d…
"Recently, open-vocabulary image classification by vision language pre-training has demonstrated incredible achievements, that the model can classify arbitrary categories without seeing additional annotated images of that category. However, it is still unclear how to make the open-vocabulary recogni…
Optimizing an objective function with uncertainty awareness is well-known to improve the accuracy and confidence of optimization solutions. Meanwhile, another relevant but very different question remains yet open: how to model and quantify the uncertainty of an optimization algorithm (a.k.a., optimi…
Recently, the behavior tree is gaining popularity as a robotic task-level knowledge representation. Manual design of behavior trees from scratch is tedious and cumbersome. Motivated by the need for an efficient way to reuse or transfer robot task-level knowledge, we propose a vector-space embedding…
Robustness and discrimination power are two fundamental requirements in visual object tracking. In most tracking paradigms, we find that the features extracted by the popular Siamese-like networks can not fully discriminatively model the tracked targets and distractor objects, hindering them from si…
Frozen pretrained models have become a viable alternative to the pretraining-then-finetuning paradigm for transfer learning. However, with frozen models there are relatively few parameters available for adapting to downstream tasks, which is problematic in computer vision where tasks vary significan…
Full-reference (FR) image quality assessment (IQA) evaluates the visual quality of a distorted image by measuring its perceptual difference with pristine-quality reference, and has been widely used in low level vision tasks. Pairwise labeled data with mean opinion score (MOS) are required in trainin…
This paper presents SimMIM, a simple framework for masked image modeling. We have simplified recently proposed relevant approaches, without the need for special designs, such as block-wise masking and tokenization via discrete VAE or clustering. To investigate what makes a masked image modeling task…
We present techniques for scaling Swin Transformer [??] up to 3 billion parameters and making it capable of training with images of up to 1,536x1,536 resolution. By scaling up capacity and resolution, Swin Transformer sets new records on four representative vision benchmarks: 84.0% top-1 accuracy on…
The vision community is witnessing a modeling shift from CNNs to Transformers, where pure Transformer architectures have attained top accuracy on the major video recognition benchmarks. These video models are all built on Transformer layers that globally connect patches across the spatial and tempor…
We introduce MixTraining, a new training paradigm for object detection that can improve the performance of existing detectors for free. MixTraining enhances data augmentation by utilizing augmentations of different strengths while excluding the strong augmentations of certain training samples that m…
Neural machine translation (NMT) models are data-driven and require large-scale training corpus. In practical applications, NMT models are usually trained on a general domain corpus and then fine-tuned by continuing training on the in-domain corpus. However, this bears the risk of catastrophic forge…
A well-known issue of Batch Normalization is its significantly reduced effectiveness in the case of small mini-batch sizes. When a mini-batch contains few examples, the statistics upon which the normalization is defined cannot be reliably estimated from it during a training iteration. To address thi…
Designing novel protein sequences for a desired 3D topological fold is a fundamental yet non-trivial task in protein engineering. Challenges exist due to the complex sequence–fold relationship, as well as the difficulties to capture the diversity of the sequences (therefore structures and functions)…
Recently, directly detecting 3D objects from 3D point clouds has received increasing attention. To extract object representation from an irregular point cloud, existing methods usually take a point grouping step to assign the points to an object candidate so that a PointNet-like network could be use…
Contrastive learning methods for unsupervised visual representation learning have reached remarkable levels of transfer performance. We argue that the power of contrastive learning has yet to be fully unleashed, as current methods are trained only on instance-level pretext tasks, leading to represen…
Paraphrases refer to texts that convey the same meaning with different expression forms. Pivot-based methods, also known as the round-trip translation, have shown promising results in generating high-quality paraphrases. However, existing pivot-based methods all rely on language as the pivot, where…
In this paper, a learning-based whole-body loco-motion controller is proposed, which enables quadruped robots to perform running in the style of real animals. We use a low-level controller based on multi-rigid body dynamics to calculate desired torques for each joint, while the high-level neural net…
This paper presents a new vision Transformer, called Swin Transformer, that capably serves as a general-purpose backbone for computer vision. Challenges in adapting Transformer from language to vision arise from differences between the two domains, such as large variations in the scale of visual ent…
Recent advances of network architecture for point cloud processing are mainly driven by new designs of local aggregation operators. However, the impact of these operators to network performance is not carefully investigated due to different overall network architecture and implementation details in…
The non-local block is a popular module for strengthening the context modeling ability of a regular convolutional neural network. This paper first studies the non-local block in depth, where we find that its attention computation can be split into two terms, a whitened pairwise term accounting for t…
How do humans recognize an object in a piece of video? Due to the deteriorated quality of single frame, it may be hard for people to identify an occluded object in this frame by just utilizing information within one image. We argue that there are two important cues for humans to recognize objects in…
In this paper, we unconventionally propose to adopt appropriate negative-margin to softmax loss for few-shot classification, which surprisingly works well for the open-set scenarios of few-shot classification. We then provide the intuitive explanation and the theoretical proof to understand why nega…
This paper presents parametric instance classification (PIC) for unsupervised visual feature learning. Unlike the state-of-the-art approaches which do instance discrimination in a dual-branch non-parametric fashion, PIC directly performs a one-branch parametric instance classification, revealing a s…
Verification and regression are two general methodologies for prediction in neural networks. Each has its own strengths: verification can be easier to infer accurately, and regression is more efficient and applicable to continuous target variables. Hence, it is often beneficial to carefully combine…
We investigate the task of learning blind image denoising networks from an unpaired set of clean and noisy images. Such problem setting generally is practical and valuable considering that it is feasible to collect unpaired noisy and clean images in most real-world applications. And we further assum…
We introduce a new pre-trainable generic representation for visual-linguistic tasks, called Visual-Linguistic BERT (VL-BERT for short). VL-BERT adopts the simple yet powerful Transformer model as the backbone, and extends it to take both visual and linguistic embedded features as input. In it, each…
Learning to optimize has emerged as a powerful framework for various optimization and machine learning tasks. Current such "meta-optimizers" often learn in the space of continuous optimization algorithms that are point-based and uncertainty-unaware. To overcome the limitations, we propose a meta-opt…
Deep hashing enables computation and memory efficient image search through end-to-end learning of feature representations and binary codes. While linear scan over binary hash codes is more efficient than over the high-dimensional representations, its linear-time complexity is still unacceptable for…
Recent progress in multiple object tracking (MOT) has shown that a robust similarity score is a key to the success of trackers. A good similarity score is expected to reflect multiple cues, e.g. appearance, location, and topology, over a long period of time. However, these cues are heterogeneous, ma…
Cross-modal hashing enables similarity retrieval across different content modalities, such as searching relevant images in response to text queries. It provides with the advantages of computation efficiency and retrieval quality for multimedia retrieval. Hamming space retrieval enables efficient con…
Due to its computation efficiency and retrieval quality, hashing has been widely applied to approximate nearest neighbor search for large-scale image retrieval, while deep hashing further improves the retrieval quality by end-to-end representation learning and hash coding. With compact hash codes, H…
Deep learning to hash improves image retrieval performance by end-to-end representation learning and hash coding from training data with pairwise similarity information. Subject to the scarcity of similarity information that is often expensive to collect for many application domains, existing deep l…
Compact coding has been widely applied to approximate nearest neighbor search for large-scale image retrieval, due to its computation efficiency and retrieval quality. This paper presents a compact coding solution with a focus on the deep learning to quantization approach, which improves retrieval q…
Recent studies reveal that a deep neural network can learn transferable features which generalize well to novel tasks for domain adaptation. However, as deep features eventually transition from general to specific along the network, the feature transferability drops significantly in higher layers wi…