相关论文: Efficient Medical Vision-Language Alignment Throug…

Ultrasound foundation models have achieved strong performance on structured prediction tasks but remain exclusively vision-based, limiting zero-shot and few-shot transfer to novel tasks where task-specific annotation is scarce. We address…

Vision-Language Models (VLMs) achieve strong cross-modal performance, yet recent evidence suggests they over-rely on textual descriptions while under-utilizing visual evidence -- a phenomenon termed ``text shortcut learning.'' We propose an…

Attention models are widely used in Vision-language (V-L) tasks to perform the visual-textual correlation. Humans perform such a correlation with a strong linguistic understanding of the visual world. However, even the best performing…

The success of CLIP-like vision-language models (VLMs) on natural images has inspired medical counterparts, yet existing approaches largely fall into two extremes: specialist models trained on single-domain data, which capture…

How well are unimodal vision and language models aligned? Although prior work have approached answering this question, their assessment methods do not directly translate to how these models are used in practical vision-language tasks. In…

3D medical vision-language (VL) pretraining has shown potential in radiology by leveraging large-scale multimodal datasets with CT-report pairs. However, existing methods primarily rely on a global VL alignment directly adapted from 2D…

Word alignment is essential for the downstream cross-lingual language understanding and generation tasks. Recently, the performance of the neural word alignment models has exceeded that of statistical models. However, they heavily rely on…

Active Learning (AL) has emerged as a powerful approach for minimizing labeling costs by selectively sampling the most informative data for neural network model development. Effective AL for large-scale vision-language models necessitates…

Recent Multimodal Large Language Models (MLLMs) have demonstrated significant progress in perceiving and reasoning over multimodal inquiries, ushering in a new research era for foundation models. However, vision-language misalignment in…

Vision-language models, while effective in general domains and showing strong performance in diverse multi-modal applications like visual question-answering (VQA), struggle to maintain the same level of effectiveness in more specialized…

Contrastive Language-Image Pre-training (CLIP) has demonstrated strong generalization across a wide range of visual tasks by leveraging large-scale English-image pairs. However, its extension to low-resource languages remains limited due to…

Medical Visual Question Answering (Medical-VQA) aims to to answer clinical questions regarding radiology images, assisting doctors with decision-making options. Nevertheless, current Medical-VQA models learn cross-modal representations…

Integrating image and text data through multi-modal learning has emerged as a new approach in medical imaging research, following its successful deployment in computer vision. While considerable efforts have been dedicated to establishing…

Cross-modal alignment is essential for vision-language pre-training (VLP) models to learn the correct corresponding information across different modalities. For this purpose, inspired by the success of masked language modeling (MLM) tasks…

Cross-modal medical image-report retrieval task plays a significant role in clinical diagnosis and various medical generative tasks. Eliminating heterogeneity between different modalities to enhance semantic consistency is the key challenge…

In recent years, zero-shot and few-shot learning in visual grounding have garnered considerable attention, largely due to the success of large-scale vision-language pre-training on expansive datasets such as LAION-5B and DataComp-1B.…

Vision-Language Models (VLMs) such as CLIP demonstrate strong zero-shot generalization, but their performance significantly degrades in cross-domain scenarios with scarce target-domain training data (Cross-Domain Few-Shot Learning, CDFSL).…

This paper demonstrates that a progressively aligned language model can effectively bridge frozen vision encoders and large language models (LLMs). While the fundamental architecture and pre-training methods of vision encoders and LLMs have…

Pretrained on web-scale open data, VLMs offer powerful capabilities for solving downstream tasks after being adapted to task-specific labeled data. Yet, data labeling can be expensive and may demand domain expertise. Active Learning (AL)…

Defending pre-trained vision-language models (VLMs), such as CLIP, against adversarial attacks is crucial, as these models are widely used in diverse zero-shot tasks, including image classification. However, existing adversarial training…