58 accepted papers
Image personalization enables customizing Text-to-Image models with a few reference images but is plagued by "concept coupling"—the model creating spurious associations between a subject and its context. Existing methods tackle this indirectly, forcing a trade-off between personalization fidelity an…
The rapid evolution of Large Language Models (LLMs) has empowered even non-programmers to create visually appealing frontend mini-games with a single instruction. However, open-source models significantly lag behind proprietary counterparts in this domain. The core bottleneck is the lack of an evalu…
Estimating the 6DoF pose of a novel object with a single reference view is challenging due to occlusions, view-point changes, and outliers. A core difficulty lies in finding robust cross-view correspondences, as existing methods often rely on discrete one-to-one matching that is non-differentiable a
Assembly action understanding is a key enabler for effective human-robot collaborative assembly, yet it remains challenging due to subtle motions and fine-grained hand–object interactions. We adapt vision-language models (VLMs) to this challenging domain with Compositional Context Fine-Tuning (CCFT)…
Graph Domain Adaptation (GDA) transfers knowledge from labeled source graphs to unlabeled target graphs, addressing the challenge of label scarcity. However, existing GDA methods typically assume that both source and target graphs exhibit homophily, leading existing methods to perform poorly when he
Knowledge distillation (KD) transfers the ``dark knowledge
The limited availability of high-quality training data poses a persistent challenge for synthetic aperture radar (SAR) target classification. Existing data augmentation methods mainly adopt a simplistic application of GAN-based style transfer techniques to directly synthesize pseudo-SAR images from
High-resolution visual representation learning remains challenging due to the quadratic complexity of Vision Transformers and the limitations of existing efficient approaches, where fixed scanning patterns in recent Mamba-based models hinder content-adaptive perception. To address these limitations,…
Prototype-based personalized federated learning methods have emerged as a promising strategy due to their ability to represent client-specific class characteristics effectively through learned class prototypes. These prototypes capture salient features of client-local data, facilitating personalized
Dual-hand action segmentation, densely predicting actions for both hands from untrimmed videos, is essential for understanding complex bimanual activities. However, it poses several unique challenges: complex inter-hand dependencies, visual asymmetry between hands, representation conflicts where the
Large language model (LLM) watermarking has shown promise in detecting AI-generated content and mitigating misuse, with prior work claiming robustness against paraphrasing and text editing. In this paper, we argue that existing evaluations are not sufficiently adversarial, obscuring critical vulnera…
Large-scale chemical reaction datasets are crucial for AI research in chemistry. However, existing chemical reaction data often exist as images within papers, making them not machine-readable and unusable for training machine learning models. In response to this challenge, we propose the RxnCaption
Large language models (LLMs) have demonstrated strong coding capabilities but still struggle to solve competitive programming problems correctly in a single attempt. Execution-based re-ranking offers a promising test-time scaling strategy, yet existing methods are constrained by either difficult tes…
Zero-Shot Object Navigation (ZSON) agents rely on continuously updated internal states to support long-horizon planning and decision-making. However, existing methods heavily depend on the observational outputs of vision-language models (VLMs) during state updates and lack explicit validation of per…
Diffusion models have demonstrated powerful capability as a versatilist for dense vision tasks, yet the generalization ability to unseen domains remains rarely explored. This paper presents HarDiff, an efficient frequency learning scheme, so as to advance generalizable paradigms for diffusion based…
Reconstructing atmospheric surface \text CO _2 is crucial for understanding climate dynamics and informing global mitigation strategies. Traditional inversion models achieve precise global \text CO _2 reconstruction but rely heavily on uncertain prior estimates of fluxes and emissions. Inspired by r…
Negative transfer (NF) is a critical challenge in personalized federated learning (pFL). Existing methods primarily focus on adapting local data distribution on the client side, which can only resist NF, rather than avoid NF itself. To tackle NF at its root, we investigate its mechanism through the…
Domain generalization aims to learn a representation from the source domain, which can be generalized to arbitrary unseen target domains. A fundamental challenge for visual domain generalization is the domain gap caused by the dramatic style variation whereas the image content is stable. The realm…
Image restoration is a fundamental task in computer vision and machine learning, which learns a mapping between the clear images and the degraded images under various conditions (e.g., blur, low-light, haze). Yet, most existing image restoration methods are highly restricted by the requirement of de…
Server aggregation conflict is a key challenge in personalized federated learning (PFL). While existing PFL methods have achieved significant progress with shallow base models (e.g., four-layer CNNs), they often overlook the negative impacts of deeper base models on personalization mechanisms. In th…
The success of Graph Neural Networks (GNNs) leverages the homophily principle, where connected nodes share similar features and labels. However, this assumption breaks down in heterophilic graphs, where same-class nodes are often distributed across distant neighborhoods rather than immediate connect…
Intraoperative 2D/3D registration, which aligns preoperative CT scans with intraoperative X-ray images, is critical for surgical navigation. However, existing methods require extensive preoperative training (several hours), making them unsuitable for emergency surgeries where minutes significantly i…
Many existing personalized federated learning (PFL) methods utilize clustering-based aggregation to group clients with similar data characteristics, improving model performance by promoting collaboration among clients with shared features. While this method effectively mitigates some challenges pose…
Pre-trained Vision-Language Models (VLMs) such as CLIP have shown excellent generalization abilities. However, adapting these large-scale models to downstream tasks while preserving their generalization capabilities remains challenging. Although prompt learning methods have shown promise, they suffe…
Knowledge distillation enhances student performance by transferring knowledge from teachers. However, existing approaches often suffer from a lack of knowledge diversity. To address this issue, we propose Cross-Modal Insights Knowledge Distillation (CIKD), a novel framework that leverages the cross-…
Domain generalization aims to train models that perform robustly on unseen target domains without access to target data. The realm of vision-language foundation model has opened a new venue owing to its inherent out-of-distribution generalization capability. However, the static alignment to class-l…
Reconstructing ocean surface nutrients from sparse observations is critical for understanding long-term biogeochemical cycles. Most prior work focuses on reconstructing atmospheric fields and treats the reconstruction problem as image inpainting, assuming smooth, single-scale dynamics. In contrast,…
Night-time scene segmentation is a critical yet challenging task in the real-world applications, primarily due to the complicated lighting conditions. However, existing methods lack sufficient generalization ability to unseen nigh-time scenes with varying illumination.In light of this issue, we focu…
Automatically generating presentations from documents is a challenging task that requires accommodating content quality, visual appeal, and structural coherence. Existing methods primarily focus on improving and evaluating the content quality in isolation, overlooking visual appeal and structural co
The rapid growth of publicly available data has fueled deep learning advancements but also raises concerns about unauthorized data usage. Unlearnable Examples (UEs) have emerged as a data protection strategy that introduces imperceptible perturbations to prevent unauthorized learning. However, most…
Long-form egocentric video understanding provides rich contextual information and unique insights into long-term human behaviors, holding significant potential for applications in embodied intelligence, long-term activity analysis, and personalized assistive technologies. However, existing benchmark
Transformer models, such as BERT, GPT, and ViT, have been applied to a wide range of areas in recent years, due to their efficacy. In order to improve the training efficiency of Transformer models, different distributed training approaches have been proposed, like Megatron-LM [8]. However, when mult…
Pitch estimation plays a critical role in various fields from speech analysis and synthesis to medical diagnosis. Despite the importance of pitch estimation, the evaluation of pitch estimation methods often yields inconsistent results and unfair comparisons. This inconsistency largely stems from the…
The class imbalance problem, which is prevalent in medical image datasets, seriously affects the diagnostic effectiveness of deep learning-based network models. Recently, the method based on two-stage learning has produced promising results in solving class imbalance. In two-stage learning, the lear…
In current synthetic aperture radar (SAR) object classification, one of the major challenges is the severe overfitting issue due to the limited dataset (few-shot) and noisy data. Considering the advantages of knowledge distillation as a learned label smoothing regularization, this paper proposes a n…
Recognising and tracking human actions from videos is crucial for human-robot collaborative assembly (HRCA). However, traditional action segmentation methods suffer from limited scene adaptability, partly because they conceptualise actions as unified verb-object entities with complete semantics. To…
Most existing synthetic aperture radar (SAR) ship classification technologies heavily rely on correctly labeled data, ignoring the discriminate features of unlabeled SAR ship images. Even though researchers try to enrich CNN-based features by introducing traditional handcrafted features, existing me…
Multi-task visual scene understanding aims to leverage the relationships among a set of correlated tasks which are solved simultaneously by embedding them within a uni- fied network. However most existing methods give rise to two primary concerns from a task-level perspective: (1) the lack of task-i…
The emerging vision foundation model (VFM) has inherited the ability to generalize to unseen images. Nevertheless, the key challenge of domain-generalized semantic segmentation (DGSS) lies in the domain gap attributed to the cross-domain styles, i.e., the variance of urban landscape and environment…
Domain generalized medical image segmentation requires models to learn from multiple source domains and generalize well to arbitrary unseen target domain. Such a task is both technically challenging and clinically practical, due to the domain shift problem (i.e., images are collected from different…
Disease grading is a crucial task in medical image analysis. Due to the continuous progression of diseases, i.e., the variability within the same level and the similarity between adjacent stages, accurate grading is highly challenging. Furthermore, in real-world scenarios, models trained on limited…
The rapid development of intelligent systems for eye disease diagnosis decreases the risk of people suffering from vision impairment. However, the superior discrimination ability of existing retinal disease diagnosis methods heavily relies on the large-scale high-quality annotations. In this work, w…
A versatile medical image segmentation model applicable to images acquired with diverse equipment and protocols can facilitate model deployment and maintenance. However building such a model typically demands a large diverse and fully annotated dataset which is challenging to obtain due to the labor…
The rigid and straight nature of conventional surgical drills and screwdrivers makes it difficult to access the posterior mandible for fracture reduction without the creation of facial incisions. To assist transoral mandibular fracture reduction in hard-to-reach areas, we propose a shared-control de…
Accurate reconstruction of cortical surfaces from brain magnetic resonance images (MRIs) remains a challenging task due to the notorious partial volume effect in brain MRIs and the cerebral cortex's thin and highly folded patterns. Although many promising deep learning-based cortical surface reconst…
The conventional few-shot classification aims at learning a model on a large labeled base dataset and rapidly adapting to a target dataset that is from the same distribution as the base dataset. However, in practice, the base and the target datasets of few-shot classification are usually from differ…
Pre-trained vision-language models have inspired much research on few-shot learning. However, with only a few training images, there exist two crucial problems: (1) the visual feature distributions are easily distracted by class-irrelevant information in images, and (2) the alignment between the vis…
Dynamically grouping sensory information into structured entities is essential for understanding the world of combinatorial nature. However, the grouping ability and therefore combinatorial generalization are still challenging artificial neural networks. Inspired by the evidence that successful grou…
Understanding comprehensive assembly knowledge from videos is critical for futuristic ultra-intelligent industry. To enable technological breakthrough, we present HA-ViD – the first human assembly video dataset that features representative industrial assembly scenarios, natural procedural knowledge…
Compositional generalization is a basic mechanism in human language learning, which current neural networks struggle with. A recently proposed Disentangled sequence-to-sequence model (Dangle) shows promising generalization capability by learning specialized encodings for each decoding step. We intro…
The binding problem is one of the fundamental challenges that prevent the artificial neural network (ANNs) from a compositional understanding of the world like human perception, because disentangled and distributed representations of generative factors can interfere and lead to ambiguity when comple…
There is mounting evidence that existing neural network models, in particular the very popular sequence-to-sequence architecture, struggle to systematically generalize to unseen compositions of seen components. We demonstrate that one of the reasons hindering compositional generalization relates to…
Although neural sequence-to-sequence models have been successfully applied to semantic parsing, they fail at compositional generalization, i.e., they are unable to systematically generalize to unseen compositions of seen components. Motivated by traditional semantic parsing where compositionality is…
Segmentation of skin lesions is important for disease diagnoses and treatment planning. Over the years, semi-supervised methods using pseudo labels have boosted the segmentation performance with limited labeled data and abundant unlabeled data. However, the unreliable targets in pseudo labels might…
Compressed Sensing MRI (CS-MRI) aims at reconstrcuting de-aliased images from sub-Nyquist sampling k-space data to accelerate MR Imaging. Inspired by recent deep learning methods, we propose a Cascaded Dilated Dense Network (CDDN) for MRI reconstruction. Dense blocks with residual connection are use…
Accurate detection of nodules in CT images is vital for lung cancer diagnosis, which greatly influences the patient's chance for survival. Motivated by successful application of convolutional neural networks (CNNs) on natural images, we propose a computer-aided diagnosis (CAD) system for simultaneou…