Related papers: LLaVA-SP: Enhancing Visual Representation with Vis…

Vision model have gained increasing attention due to their simplicity and efficiency in Scene Text Recognition (STR) task. However, due to lacking the perception of linguistic knowledge and information, recent vision models suffer from two…

Generative Large Multimodal Models (LMMs) like LLaVA and Qwen-VL excel at a wide variety of vision-language (VL) tasks. Despite strong performance, LMMs' generative outputs are not specialized for vision-language classification tasks (i.e.,…

Vision-language models (VLMs) have made significant progress in image classification by training with large-scale paired image-text data. Their performances largely depend on the prompt quality. While recent methods show that visual…

Vision transformers (ViTs) encoding an image as a sequence of patches bring new paradigms for semantic segmentation.We present an efficient framework of representation separation in local-patch level and global-region level for semantic…

Recent advances achieved by deep learning models rely on the independent and identically distributed assumption, hindering their applications in real-world scenarios with domain shifts. To tackle this issue, cross-domain learning aims at…

Conversation agents powered by large language models are revolutionizing the way we interact with visual data. Recently, large vision-language models (LVLMs) have been extensively studied for both images and videos. However, these studies…

Large multimodal models (LMMs) suffer significant computational challenges due to the high cost of Large Language Models (LLMs) and the quadratic complexity of processing long vision token sequences. In this paper, we explore the spatial…

Multimodal Large Language Models (MLLMs) have achieved notable gains in various tasks by incorporating Chain-of-Thought (CoT) reasoning in language spaces. Recent work extends this direction by leveraging external tools for visual editing,…

CLIP is a seminal multimodal model that maps images and text into a shared representation space through contrastive learning on billions of image-caption pairs. Inspired by the rapid progress of large language models (LLMs), we investigate…

Whole-slide images (WSIs) in pathology can reach up to 10,000 x 10,000 pixels, posing significant challenges for multimodal large language model (MLLM) due to long context length and high computational demands. Previous methods typically…

Prompt learning methods have significantly extended the transferability of pre-trained Vision-Language Models (VLMs) like CLIP for various downstream tasks. These methods adopt handcraft templates or learnable vectors to provide text or…

Vision-Language Pre-training (VLP) models like CLIP have achieved remarkable success in computer vision and particularly demonstrated superior robustness to distribution shifts of 2D images. However, their robustness under 3D viewpoint…

Currently, inspired by the success of vision-language models (VLMs), an increasing number of researchers are focusing on improving VLMs and have achieved promising results. However, most existing methods concentrate on optimizing the…

Existing Multimodal Large Language Models (MLLMs) suffer from increased inference costs due to the additional vision tokens introduced by image inputs. In this work, we propose Visual Consistency Learning (ViCO), a novel training algorithm…

Multi-label image recognition is a fundamental task in computer vision. Recently, vision-language models have made notable advancements in this area. However, previous methods often failed to effectively leverage the rich knowledge within…

With advancements in data availability and computing resources, Multimodal Large Language Models (MLLMs) have showcased capabilities across various fields. However, the quadratic complexity of the vision encoder in MLLMs constrains the…

Vision-Language Pre-training (VLP) methods based on object detection enjoy the rich knowledge of fine-grained object-text alignment but at the cost of computationally expensive inference. Recent Visual-Transformer (ViT)-based approaches…

Pre-trained Vision-Language Models (VLMs), like CLIP, exhibit strong generalization ability to downstream tasks but struggle in few-shot scenarios. Existing prompting techniques primarily focus on global text and image representations, yet…

Recent research has shown that CLIP models struggle with visual reasoning tasks that require grounding compositionality, understanding spatial relationships, or capturing fine-grained details. One natural hypothesis is that the CLIP vision…

Vision-language models, such as CLIP, have achieved significant success in aligning visual and textual representations, becoming essential components of many multi-modal large language models (MLLMs) like LLaVA and OpenFlamingo. However,…