Related papers: Uncertainty-Aware Spatial Color Correlation for Lo…

Deep neural networks have shown exceptional performance in various tasks, but their lack of robustness, reliability, and tendency to be overconfident pose challenges for their deployment in safety-critical applications like autonomous…

Unsupervised domain adaptation (UDA) aims to adapt existing models of the source domain to a new target domain with only unlabeled data. Most existing methods suffer from noticeable negative transfer resulting from either the error-prone…

Overfitting remains a significant challenge in deep learning, often arising from data outliers, noise, and limited training data. To address this, the Divide2Conquer (D2C) method was previously proposed, which partitions training data into…

Diffusion language models (DLMs) expose their denoising trajectories, offering a natural handle for inference-time control; accordingly, an ideal hallucination mitigation framework should intervene during generation using this model-native…

Images captured under low-light conditions present significant limitations in many applications, as poor lighting can obscure details, reduce contrast, and hide noise. Removing the illumination effects and enhancing the quality of such…

Many learning-based low-light image enhancement (LLIE) algorithms are based on the Retinex theory. However, the Retinex-based decomposition techniques in such models introduce corruptions which limit their enhancement performance. In this…

Collaborative Object Detection (COD) and collaborative perception can integrate data or features from various entities, and improve object detection accuracy compared with individual perception. However, adversarial attacks pose a potential…

Multimodal Large Language Models (MLLMs) have notably enhanced the performance of Multimodal Sentiment Analysis (MSA), yet their massive parameter scale leads to excessive resource consumption in training and inference, severely limiting…

Unsupervised Domain Adaptation (UDA) aims to adapt a model trained on a labeled source domain to an unlabeled target domain by addressing the domain shift. Existing Unsupervised Domain Adaptation (UDA) methods often fall short in fully…

Diffusion models, known for their powerful generative capabilities, play a crucial role in addressing real-world super-resolution challenges. However, these models often focus on improving local textures while neglecting the impacts of…

Alzheimer's disease (AD) is an irreversible neurodegenerative disorder, and early diagnosis is critical for timely intervention. However, most existing classification frameworks face challenges in multicenter studies, as they often neglect…

Domain shift widely exists in the visual world, while modern deep neural networks commonly suffer from severe performance degradation under domain shift due to the poor generalization ability, which limits the real-world applications. The…

Reconstructing dynamic 4D scenes is an important yet challenging task. While 3D foundation models like VGGT excel in static settings, they often struggle with dynamic sequences where motion causes significant geometric ambiguity. To address…

We introduce a novel uncertainty-aware multimodal segmentation framework that leverages both radiological images and associated clinical text for precise medical diagnosis. We propose a Modality Decoding Attention Block (MoDAB) with a…

Illumination uniformity is a critical parameter for excitation and data extraction quality in widefield biological imaging applications. However, typical imaging systems suffer from spatial and spectral non-uniformity due to non-ideal…

Large Language Models (LLMs) are prone to hallucination, particularly in long-form generations. A promising direction to mitigate hallucination is to teach LLMs to express uncertainty explicitly when they lack sufficient knowledge. However,…

Accurate lesion segmentation is crucial for clinical diagnosis and treatment planning. However, lesions often resemble surrounding tissues and exhibit ill-defined boundaries, leading to unstable predictions in boundary/transition regions.…

Raw low light image enhancement (LLIE) has achieved much better performance than the sRGB domain enhancement methods due to the merits of raw data. However, the ambiguity between noisy to clean and raw to sRGB mappings may mislead the…

In recent years, the neural implicit surface has emerged as a powerful representation for multi-view surface reconstruction due to its simplicity and state-of-the-art performance. However, reconstructing smooth and detailed surfaces in…

Existing displacement strategies in semi-supervised segmentation only operate on rectangular regions, ignoring anatomical structures and resulting in boundary distortions and semantic inconsistency. To address these issues, we propose UCAD,…