相关论文: Efficient Vision-and-Language Pre-training with Te…

The rapid advancement of Multimodal Large Language Models (MLLMs) has led to remarkable performances across various domains. However, this progress is accompanied by a substantial surge in the resource consumption of these models. We…

Pursuing training-free open-vocabulary semantic segmentation in an efficient and generalizable manner remains challenging due to the deep-seated spatial bias in CLIP. To overcome the limitations of existing solutions, this work moves beyond…

Multimodal large language models (MLLMs) suffer from high computational costs due to excessive visual tokens, particularly in high-resolution and video-based scenarios. Existing token reduction methods typically focus on isolated pipeline…

Learning a versatile language-image model is computationally prohibitive under a limited computing budget. This paper delves into the \emph{efficient language-image pre-training}, an area that has received relatively little attention…

We propose a simple strategy for masking image patches during visual-language contrastive learning that improves the quality of the learned representations and the training speed. During each iteration of training, we randomly mask clusters…

Text spotting, a task involving the extraction of textual information from image or video sequences, faces challenges in cross-domain adaption, such as image-to-image and image-to-video generalization. In this paper, we introduce a new…

This paper examines the problems of severe image-text misalignment and high redundancy in the widely-used large-scale Vision-Language Pre-Training (VLP) datasets. To address these issues, we propose an efficient and straightforward…

Vision Transformers (ViTs) have shown impressive performance and have become a unified backbone for multiple vision tasks. However, both the attention mechanism and multi-layer perceptrons (MLPs) in ViTs are not sufficiently efficient due…

Recent progress has shown great potential of visual prompt tuning (VPT) when adapting pre-trained vision transformers to various downstream tasks. However, most existing solutions independently optimize prompts at each layer, thereby…

Prompt tuning, which involves training a small set of parameters, effectively enhances the pre-trained Vision-Language Models (VLMs) to downstream tasks. However, they often come at the cost of flexibility and adaptability when the tuned…

Vision Transformers (ViTs) are becoming more popular and dominating technique for various vision tasks, compare to Convolutional Neural Networks (CNNs). As a demanding technique in computer vision, ViTs have been successfully solved various…

Document understanding and GUI interaction are among the highest-value applications of Vision-Language Models (VLMs), yet they impose exceptionally heavy computational burden: fine-grained text and small UI elements demand high-resolution…

Recently, Vision Transformer (ViT) has achieved promising performance in image recognition and gradually serves as a powerful backbone in various vision tasks. To satisfy the sequential input of Transformer, the tail of ViT first splits…

Vision transformers have demonstrated the potential to outperform CNNs in a variety of vision tasks. But the computational and memory requirements of these models prohibit their use in many applications, especially those that depend on…

The groundbreaking performance of transformers in Natural Language Processing (NLP) tasks has led to their replacement of traditional Convolutional Neural Networks (CNNs), owing to the efficiency and accuracy achieved through the…

The ubiquitous and demonstrably suboptimal choice of resizing images to a fixed resolution before processing them with computer vision models has not yet been successfully challenged. However, models such as the Vision Transformer (ViT)…

Vision transformers (ViTs) have recently obtained success in many applications, but their intensive computation and heavy memory usage at both training and inference time limit their generalization. Previous compression algorithms usually…

Large vision-language models (LVLMs) generally contain significantly more visual tokens than their textual counterparts, resulting in a considerable computational burden. Recent efforts have been made to tackle this issue by pruning visual…

Multimodal large language models (MLLMs) have demonstrated remarkable potential for enhancing scene understanding in autonomous driving systems through powerful logical reasoning capabilities. However, the deployment of these models faces…

Vision-and-language pre-training (VLP) models have experienced a surge in popularity recently. By fine-tuning them on specific datasets, significant performance improvements have been observed in various tasks. However, full fine-tuning of…