55 accepted papers
Context-dependent (CD) tasks demand the model to have advanced visual understanding ability, such as recognizing camouflaged objects and medical lesions. Current CD methods rely heavily on pixel-level annotated training sets, neglecting issues from redundant samples and the high annotation costs. In
Cross-subject generalization in biomedical time-series (BTS) refers to training on data from some subjects and testing on unseen subjects. The key challenge is to suppress subject-specific variability in BTS representations. Most existing methods implicitly suppress the variability through model bui…
Distributed optimization over time-varying directed graphs has shown promising performance in addressing challenges posed by complex communication constraints in real-world scenarios. In many practical settings, however, the direct application of distributed optimization algorithms encounters additi…
Preference-based reinforcement learning (PbRL) can help avoid sophisticated reward designs and align better with human intentions, showing great promise in various real-world applications. However, obtaining human feedback for preferences can be expensive and time-consuming, which forms a strong bar…
The rise of large language models has led to significant performance breakthroughs in named entity recognition (NER) for high-resource languages, yet there remains substantial room for improvement in low- and medium-resource languages. Existing multilingual NER methods face severe language interfere…
As large language models (LLMs) continue to improve in reasoning and decision-making, there is a growing need for realistic and interactive environments where their abilities can be rigorously evaluated. We present VirtualEnv, a next-generation simulation platform built on Unreal Engine 5 that enabl
Bilevel optimization has garnered significant attention in the machine learning community recently, particularly regarding the development of efficient numerical methods. While substantial progress has been made in developing efficient algorithms for optimistic bilevel optimization, the study of me…
This letter proposes a novel linear online identification framework for the spherical robot to address the modeling difficulties posed by nonlinearity and time-varying characteristics. Firstly, the Koopman theory is applied to the spherical robot to build a linear model to approximate the nonlineari
Adversarial learning is a widely used paradigm in machine learning, often formulated as a min-max optimization problem where the inner maximization imposes adversarial constraints to guide the outer learner toward more robust solutions. This framework underlies methods such as Sharpness-Aware Minimi…
Large Vision-Language Models (LVLMs) have recently demonstrated amazing success in multi-modal tasks, including advancements in Multi-modal Chain-of-Thought (MCoT) reasoning. Despite these successes, current benchmarks still follow a traditional paradigm with multi-modal input and text-modal output,…
End-to-end automatic speech recognition (ASR) based on deep learning has achieved impressive progress in recent years. However, the performance of ASR foundation model often degrades significantly on out-of-domain data due to real-world domain shifts. Test-Time Adaptation (TTA) methods aim to mitiga
Bilevel optimization is a powerful tool for many machine learning problems, such as hyperparameter optimization and meta-learning. Estimating hypergradients (also known as implicit gradients) is crucial for developing gradient-based methods for bilevel optimization. In this work, we propose a comput…
Electroencephalography (EEG) is a time-series signal containing semantic information that can be used to determine human brain activities. Artifacts within EEG data can interfere with the intrinsic distribution of this semantic information, so removing artifacts is crucial for improving EEG analysis…
Real-world infrared imagery presents unique challenges for vision-language models due to the scarcity of aligned text data and domain-specific characteristics. Although existing methods have advanced the field, their reliance on synthetic infrared images generated through style transfer from visible…
In the field of large language model (LLM) post-training, the effectiveness of utilizing synthetic data generated by the LLM itself has been well-presented. However, a key question remains unaddressed: what essential information should such self-generated data encapsulate? Existing approaches only p…
Current camouflaged object detection methods predominantly follow discriminative segmentation paradigms and heavily rely on predefined categories present in the training data, limiting their generalization to unseen or emerging camouflage objects. This limitation is further compounded by the labor-i…
Stance detection, a critical task in Natural Language Processing (NLP), aims to identify the attitude expressed in text toward specific targets. Despite advancements in Large Language Models (LLMs), challenges such as limited interpretability and handling nuanced content persist. To address these is
Stance detection is a pivotal task in Natural Language Processing (NLP), identifying textual attitudes toward various targets. Despite advances in using Large Language Models (LLMs), challenges persist due to hallucination-models generating plausible yet inaccurate content. Addressing these challeng…
Constrained bilevel optimization tackles nested structures present in constrained learning tasks like constrained meta-learning, adversarial learning, and distributed bilevel optimization. However, existing bilevel optimization methods mostly are typically restricted to specific constraint settings…
High-quality perception is crucial in autonomous driving and monitoring systems, where millimeter-wave radar and infrared cameras play important roles due to their robustness and reliability under harsh conditions. Both technologies can serve as low-cost supplements to optical image detection, impro…
Data augmentation effectively expands feature distribution in time series classification, enhancing downstream task performance. However, existing techniques often fail to maintain semantic consistency between augmented and original time series data, causing label noise and thereby degrading downstr…
This paper presents a Variable Morphing Multi-Body AUVs (VMMAUVs) concept, designed for underwater structure maintenance. This robot is capable of dynamically adjusting their structure to adapt to varying operational scenarios. The study explores two key stability mechanisms: buoyancy adjustment and
Multimodal Stance Detection (MSD) aims to determine a user’s stance - support, oppose, or neutral - toward a target by analyzing multimodal content such as texts and images from social media. Existing MSD methods struggle with generalizing to unseen targets and handling modality inconsistencies. To
Bilevel optimization, which addresses challenges in hierarchical learning tasks, has gained significant interest in machine learning. Implementing gradient descent for bilevel optimization presents computational hurdles, notably the need to compute the exact lower-level solution and the inverse Hess…
This paper presents a new approach and algorithm for solving a class of constrained Bi-Level Optimization (BLO) problems in which the lower-level problem involves constraints coupling both upper-level and lower-level variables. Such problems have recently gained significant attention due to their br…
We propose G2G, based on the global model of Generalized learning to solve the Federated Domain Generalization (FedDG) task. FedDG aims to collaboratively train a global model that can directly generalize to the unseen target domain without data sharing. Existing methods face challenges from both da…
Two-stage recommender systems play a crucial role in efficiently identifying relevant items and personalizing recommendations from a vast array of options. This paper, based on an error decomposition framework, analyzes the generalization error for two-stage recommender systems with a tree structure…
Stance detection aims at inferring an author’s attitude towards a specific target in a text. Prior methods mainly consider target-related background information for a better understanding of targets while neglecting the accompanying input texts. In this study, we propose to prompt Large Language Mod…
Multi-modal Chain-of-Thought (MCoT) requires models to leverage knowledge from both textual and visual modalities for step-by-step reasoning, which gains increasing attention. Nevertheless, the current MCoT benchmark still faces some challenges: (1) absence of visual modal reasoning, (2) single-step…
This work focuses on addressing two major challenges in the context of large-scale nonconvex Bi-Level Optimization (BLO) problems, which are increasingly applied in machine learning due to their ability to model nested structures. These challenges involve ensuring computational efficiency and provid…
While stochastic bilevel optimization methods have been extensively studied for addressing large-scale nested optimization problems in machine learning, it remains an open question whether the optimal complexity bounds for solving bilevel optimization are the same as those in single-level optimizati…
It is necessary to explore an effective point cloud completion mechanism that is of great significance for real-world tasks such as autonomous driving, robotics applications, and multi-target tracking. In this paper, we propose a point cloud completion method using a self-supervised transformer mode…
In this paper, we propose rWiFiSLAM, an indoor localisation system based on WiFi ranging measurements. Indoor localisation techniques play an important role in mobile robots when they cannot access good quality GPS signals in indoor environments. Indoor localisation also has many other applications,
Gradient methods have become mainstream techniques for Bi-Level Optimization (BLO) in learning fields. The validity of existing works heavily rely on either a restrictive Lower- Level Strong Convexity (LLSC) condition or on solving a series of approximation subproblems with high accuracy or both. In…
Taste sensation can be objectively measured using electroencephalography (EEG) or electromyography (EMG). How-ever, it is still challenging to effectively utilize the complementary information from EEG and EMG signals in taste sensation recognition. This paper proposes a bimodal fusion network (Bi-F…
Click-through rate (CTR) prediction is crucial in recommendation and online advertising systems. Existing methods usually model user behaviors, while ignoring the informative context which influences the user to make a click decision, e.g., click pages and pre-ranking candidates that inform inferenc…
Recent offline meta-reinforcement learning (meta-RL) methods typically utilize task-dependent behavior policies (e.g., training RL agents on each individual task) to collect a multi-task dataset. However, these methods always require extra information for fast adaptation, such as offline context for…
Maximum Inner Product Search (MIPS) plays an essential role in many applications ranging from information retrieval, recommender systems to natural language processing. However, exhaustive MIPS is often expensive and impractical when there are a large number of candidate items. The state-of-the-art…
Cracks are usually curve-like structures that are the focus of many computer-vision applications (e.g., road safety inspection and surface inspection of industrial facilities). The existing pixel-based crack segmentation methods rely on time-consuming and costly pixel-level annotations. And the obje…
In this letter, a general robust reference path selection method (RPSM) that can be integrated into current existing motion planning algorithms is proposed to improve the mobile performance of autonomous patrol robots. The proposed RPSM maintains a dynamic array of path candidates that contains newl
Goal-conditioned hierarchical reinforcement learning (GCHRL) provides a promising approach to solving long-horizon tasks. Recently, its success has been extended to more general settings by concurrently learning hierarchical policies and subgoal representations. Although GCHRL possesses superior exp…
Maximum Inner Product Search (MIPS) plays an important role in many applications ranging from information retrieval, recommender systems to natural language processing and machine learning. However, exhaustive MIPS is often expensive and impractical when there are a large number of candidate items.…
The ability to reuse previous policies is an important aspect of human intelligence. To achieve efficient policy reuse, a Deep Reinforcement Learning (DRL) agent needs to decide when to reuse and which source policies to reuse. Previous methods solve this problem by introducing extra components to t…
Despite the substantial progress of deep models for crack recognition, due to the inconsistent cracks in varying sizes, shapes, and noisy background textures, there still lacks the discriminative power of the deeply learned features when supervised by the cross-entropy loss. In this paper, we propos…
An adversary can fool deep neural network object detectors by generating adversarial noises. Most of the existing works focus on learning local visible noises in an adversarial "patch" fashion. However, the 2D patch attached to a 3D object tends to suffer from an inevitable reduction in attack perfo…
One controller cannot work on multiple and unknown terrains in the velocity control of the spherical robot, because the dynamic models of the robot vary on different terrains, and unmodeled dynamics and uncertainties exist in estimated dynamic models. Based on the above problem, a new velocity contr
Recently, Optimization-Derived Learning (ODL) has attracted attention from learning and vision areas, which designs learning models from the perspective of optimization. However, previous ODL approaches regard the training and hyper-training procedures as two separated stages, meaning that the hyper…
Existing gradient-based optimization methods for hyperparameter tuning can only guarantee theoretical convergence to stationary solutions when the bilevel program satisfies the condition that for fixed upper-level variables, the lower-level is strongly convex (LLSC) and smooth (LLS). This condition…
"Active learning (AL) is a label-efficient technique for training deep models when only a limited labeled set is available and the manual annotation is expensive. Implicit semantic data augmentation (ISDA) effectively extends the limited amount of labeled samples and increases the diversity of label…
Bi-level optimization model is able to capture a wide range of complex learning tasks with practical interest. Due to the witnessed efficiency in solving bi-level programs, gradient-based methods have gained popularity in the machine learning community. In this work, we propose a new gradient-based…
6D pose estimation of objects is an important part of robot grasping. The latest research trend on 6D pose estimation is to train a deep neural network to directly predict the 2D projection position of the 3D key points from the image, establish the corresponding relationship, and finally use Pespec…
Meta reinforcement learning (meta-RL) extracts knowledge from previous tasks and achieves fast adaptation to new tasks. Despite recent progress, efficient exploration in meta-RL remains a key challenge in sparse-reward tasks, as it requires quickly finding informative task-relevant experiences in bo…
In recent years, Bi-Level Optimization (BLO) techniques have received extensive attentions from both learning and vision communities. A variety of BLO models in complex and practical tasks are of non-convex follower structure in nature (a.k.a., without Lower-Level Convexity, LLC for short). However,…
In recent years, a variety of gradient-based bi-level optimization methods have been developed for learning tasks. However, theoretical guarantees of these existing approaches often heavily rely on the simplification that for each fixed upper-level variable, the lower-level solution must be a single…
In this paper we consider the collaborative ranking setting: a pool of users each provides a set of pairwise preferences over a small subset of the set of d possible items; from these we need to predict each user’s preferences for items s/he has not yet seen. We do so via fitting a rank r score matr…