20 accepted papers
Numerous studies have demonstrated that Visual Question Answering (VQA) models are vulnerable to language priors and dataset biases, often leading to spurious correlations between questions and answers. As a result, these models excessively rely on linguistic cues, neglecting essential visual inform
Real-world multimodal systems inevitably face partial observability due to sensor dropout and degradation. Standard robustness methods can improve average performance, but they often remain unreliable in rare, adverse long-tail conditions. Under a locked same-support contract, we uncover a same-supp…
Fine-grained image-text alignment is a pivotal challenge in multimodal learning, underpinning key applications such as visual question answering, image captioning, and vision-language navigation. Unlike global alignment, fine-grained alignment requires precise correspondence between localized visual
Vision Transformers (ViTs) achieve state-of-the-art performance on a wide range of vision tasks, yet they remain highly vulnerable to adversarial perturbations due to the lack of explicit region-level semantic modeling. Adversarial perturbations are typically local and spatially structured, whereas
Self-attention with separate pre- and post-projections can be a universal approximator (on compact domains) under mild conditions. Yet we observe a striking gap: an attention-only Transformer (w/o FFN layers) exhibits a marked accuracy drop relative to its standard interleaved attention--FFN baselin
Neural networks necessitate nonlinearities to achieve universal approximability. Traditional activation functions introduce nonlinearities through rigid feature rectifications. Recent self-gated variants improve traditional methods in fitting flexibility by incorporating learnable content-aware fact…
Few-shot Class Incremental Learning (FSCIL) aims to incrementally learn new classes with limited examples while retaining knowledge of previously learned classes. Recent advancements in prompt tuning for large pre-trained models have shown promise in FSCIL. However, current FSCIL methods still suffe…
Few-Shot Class-Incremental Learning (FSCIL) aims to incrementally learn new class knowledge from limited samples while preserving previously knowledge from encountered classes. However, existing FSCIL methods encounter two primary challenges: (1) inadequate adaptation, where overfitting to new class…
Existing Medical Visual Question Answering (Med-VQA) models often suffer from language biases, where spurious correlations between question types and answer categories are inadvertently established. To address these issues, we propose a novel Cause-Effect Driven Optimization framework called CEDO, t
Multimodal learning presents significant challenges arising from the unpredictable absence of modalities during both training and testing phases. Existing recovery methods struggle to leverage the available data, which can introduce additional noise during the recovery process and degrade performanc…
Language bias in Visual Question Answering (VQA) arises when models exploit spurious statistical correlations between question templates and answers, particularly in out-of-distribution scenarios, thereby neglecting essential visual cues and compromising genuine multimodal reasoning. Despite numerou…
Prompt learning is a common strategy for adapting Visual Language Models (VLMs) to downstream tasks by fine-tuning prompts for task-specific performance. However, existing methods face two key challenges: overfitting to base classes, which limits generalization to novel classes, and the dependence o…
In clinical practice, panoramic dental radiography is a widely employed imaging technique that can provide a detailed and comprehensive view of dental structures and surrounding tissues for identifying various oral anomalies. However, due to the complexity of oral anomalies and the scarcity of avail…
Class-incremental learning (CIL) enables models to learn new tasks without forgetting previously acquired knowledge. However, existing CIL approaches often struggle with inadequate adaptation to task-specific feature spaces and catastrophic forgetting of previously-acquired knowledge, compromising t…
Visual Question Answering (VQA) has garnered significant attention as a crucial link between vision and language, aimed at generating accurate responses to visual queries. However, current VQA models still struggle with the challenges of minority class collapse and spurious semantic correlations pos…
Dental caries has been widely recognized as one of the most prevalent chronic diseases in the field of public health. Despite advancements in automated diagnosis across various medical domains, it remains a substantial challenge for dental caries detection due to its inherent variability and intrica…
The feature dispersion, arising from the inherent constraints of data scarcity, has emerged as a prominent challenge in the domain of few-shot learning. In this paper, we propose a novel Self-adaptive Distribution Regularization (SADR) approach, which can adaptively bridge the semantic gaps across d…
Cross-modal hashing has garnered considerable research interest due to its rapid retrieval and low storage costs. However, the majority of existing methods suffer from the limitations of context loss and information redundancy, particularly in simulated textual environments enriched with manually an…
Medical vision-language representation learning has garnered considerable attention owing to its applicability to extracting generic representations from the image and text modality. However, it still remains challenging to acquire a more comprehensive understanding of intra- and inter-modal semanti…
Many studies on automatic speech emotion recognition (SER) have been devoted to extracting meaningful emotional features for generating emotion-relevant representations. However, they generally ignore the complementary learning of static and dynamic features, leading to limited performances. In this…