Related papers: FineViT: Progressively Unlocking Fine-Grained Perc…

In this paper, we present \textbf{Gen}erative \textbf{L}anguage-\textbf{I}mage \textbf{P}re-training (GenLIP), a minimalist generative pretraining framework for Vision Transformers (ViTs) designed for multimodal large language models…

Large Multimodal Models (LMMs) typically build on ViTs (e.g., CLIP), yet their training with simple random in-batch negatives limits the ability to capture fine-grained visual differences, particularly in geometric scenarios. To address…

Contrastive image-text models such as CLIP form the building blocks of many state-of-the-art systems. While they excel at recognizing common generic concepts, they still struggle on fine-grained entities which are rare, or even absent from…

High-resolution dense prediction enables many appealing real-world applications, such as computational photography, autonomous driving, etc. However, the vast computational cost makes deploying state-of-the-art high-resolution dense…

Multi-modal large language models (MLLMs) have shown remarkable abilities in various visual understanding tasks. However, MLLMs still struggle with fine-grained visual recognition (FGVR), which aims to identify subordinate-level categories…

Vision-language models like CLIP show impressive ability to align images and text, but their training on short, concise captions makes them struggle with lengthy, detailed descriptions. Recent advances mitigate this challenge by leveraging…

The original CLIP text encoder is limited by a maximum input length of 77 tokens, which hampers its ability to effectively process long texts and perform fine-grained semantic understanding. In addition, the CLIP text encoder lacks support…

Despite recent progress in video and language representation learning, the weak or sparse correspondence between the two modalities remains a bottleneck in the area. Most video-language models are trained via pair-level loss to predict…

CLIP has shown impressive results in aligning images and texts at scale. However, its ability to capture detailed visual features remains limited because CLIP matches images and texts at a global level. To address this issue, we propose…

Self-supervised visual foundation models produce powerful embeddings that achieve remarkable performance on a wide range of downstream tasks. However, unlike vision-language models such as CLIP, self-supervised visual features are not…

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…

Pre-trained vision-language models like CLIP have recently shown superior performances on various downstream tasks, including image classification and segmentation. However, in fine-grained image re-identification (ReID), the labels are…

Dense visual prediction tasks have been constrained by their reliance on predefined categories, limiting their applicability in real-world scenarios where visual concepts are unbounded. While Vision-Language Models (VLMs) like CLIP have…

Do we fully leverage the potential of visual encoder in Multimodal Large Language Models (MLLMs)? The recent outstanding performance of MLLMs in multimodal understanding has garnered broad attention from both academia and industry. In the…

Dense visual perception tasks have been constrained by their reliance on predefined categories, limiting their applicability in real-world scenarios where visual concepts are unbounded. While Vision-Language Models (VLMs) like CLIP have…

Large Vision Language Models (LVLMs) have demonstrated impressive zero-shot capabilities in various vision-language dialogue scenarios. However, the absence of fine-grained visual object detection hinders the model from understanding the…

Vision-Language Models (VLMs), such as CLIP, have demonstrated impressive zero-shot transfer capabilities in image-level visual perception. However, these models have shown limited performance in instance-level tasks that demand precise…

The feature maps of vision encoders are fundamental to myriad modern AI tasks, ranging from core perception algorithms (e.g. semantic segmentation, object detection, depth perception, etc.) to modern multimodal understanding in…

The Visual Language Model, known for its robust cross-modal capabilities, has been extensively applied in various computer vision tasks. In this paper, we explore the use of CLIP (Contrastive Language-Image Pretraining), a vision-language…

We empirically investigate proper pre-training methods to build good visual tokenizers, making Large Language Models (LLMs) powerful Multimodal Large Language Models (MLLMs). In our benchmark, which is curated to evaluate MLLMs visual…