Related papers: Towards a Visual-Language Foundation Model for Com…

Unpaired Image Captioning (UIC) has been developed to learn image descriptions from unaligned vision-language sample pairs. Existing works usually tackle this task using adversarial learning and visual concept reward based on reinforcement…

Foundation Models (FMs) have been successful in various computer vision tasks like image classification, object detection and image segmentation. However, these tasks remain challenging when these models are tested on datasets with…

Pathological diagnosis remains the definitive standard for identifying tumors. The rise of multimodal large models has simplified the process of integrating image analysis with textual descriptions. Despite this advancement, the substantial…

In real-world vision-language applications, practitioners increasingly rely on large, pretrained foundation models rather than custom-built solutions, despite limited transparency regarding their training data and processes. While these…

Medical Vision-language models (VLMs) have shown remarkable performances in various medical imaging domains such as histo\-pathology by leveraging pre-trained, contrastive models that exploit visual and textual information. However,…

With the increase in the use of deep learning for computer-aided diagnosis in medical images, the criticism of the black-box nature of the deep learning models is also on the rise. The medical community needs interpretable models for both…

Radiologists highly desire fully automated versatile AI for medical imaging interpretation. However, the lack of extensively annotated large-scale multi-disease datasets has hindered the achievement of this goal. In this paper, we explore…

While multimodal large language models (MLLMs) have made substantial progress in single-image spatial reasoning, multi-image spatial reasoning, which requires integration of information from multiple viewpoints, remains challenging.…

Recent years have witnessed the fast development of large-scale pre-training frameworks that can extract multi-modal representations in a unified form and achieve promising performances when transferred to downstream tasks. Nevertheless,…

Generating accurate and coherent image captions in a continual learning setting remains a major challenge due to catastrophic forgetting and the difficulty of aligning evolving visual concepts with language over time. In this work, we…

While advanced image captioning systems are increasingly describing images coherently and exactly, recent progress in continual learning allows deep learning models to avoid catastrophic forgetting. However, the domain where image…

In diagnostic reports, experts encode complex imaging data into clinically actionable information. They describe subtle pathological findings that are meaningful in their anatomical context. Reports follow relatively consistent structures,…

Methods based on Contrastive Language-Image Pre-training (CLIP) are nowadays extensively used in support of vision-and-language tasks involving remote sensing data, such as cross-modal retrieval. The adaptation of CLIP to this specific…

While Vision-Language Models (VLMs) have achieved notable progress in computational pathology (CPath), the gigapixel scale and spatial heterogeneity of Whole Slide Images (WSIs) continue to pose challenges for multimodal understanding.…

In biomedical vision-language modeling, datasets are typically mined from scientific literature, pairing compound figures with captions that are short, context-dependent, and oftern partially informative. Prior work on subfigure extraction…

We present a unified vision-language framework tailored for ENT endoscopy image analysis that simultaneously tackles three clinically-relevant tasks: image classification, image-to-image retrieval, and text-to-image retrieval. Unlike…

Contrastively trained vision-language models have achieved remarkable progress in vision and language representation learning, leading to state-of-the-art models for various downstream multimodal tasks. However, recent research has…

Pathological cell semantic segmentation is a fundamental technology in computational pathology, essential for applications like cancer diagnosis and effective treatment. Given that multiple cell types exist across various organs, with…

Due to morphological similarities, the differentiation of histologic sections of cutaneous tumors into individual subtypes can be challenging. Recently, deep learning-based approaches have proven their potential for supporting pathologists…

Background and objective: Cell-level pathological image analysis requires working with extremely small image patches (40x40 pixels), far below standard ImageNet resolutions. It remains unclear whether modern deep learning architectures and…