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

Visual Prompt Tuning (VPT) techniques have gained prominence for their capacity to adapt pre-trained Vision Transformers (ViTs) to downstream visual tasks using specialized learnable tokens termed as prompts. Contemporary VPT methodologies,…

Although Multimodal Large Language Models (MLLMs) have demonstrated promising versatile capabilities, their performance is still inferior to specialized models on downstream tasks, which makes adaptation necessary to enhance their utility.…

The Vision Transformer (ViT) has made significant strides in the field of computer vision. However, as the depth of the model and the resolution of the input images increase, the computational cost associated with training and running ViT…

Real-world applications are stretching context windows to hundreds of thousand of tokens while Large Language Models (LLMs) swell from billions to trillions of parameters. This dual expansion send compute and memory costs skyrocketing,…

Recently, reducing redundant visual tokens in vision-language models (VLMs) to accelerate VLM inference has emerged as a hot topic. However, most existing methods rely on heuristics constructed based on inter-visual-token similarity or…

Recently, the advances in vision-language models, including contrastive pretraining and instruction tuning, have greatly pushed the frontier of multimodal AI. However, owing to the large-scale and hence expensive pretraining, the efficiency…

Recently, masked image modeling (MIM) has become a promising direction for visual pre-training. In the context of vision transformers, MIM learns effective visual representation by aligning the token-level features with a pre-defined space…

Recent Vision-Language Models (VLMs) have demonstrated remarkable multimodal understanding capabilities, yet the redundant visual tokens incur prohibitive computational overhead and degrade inference efficiency. Prior studies typically…

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…

Texture, a significant visual attribute in images, has been extensively investigated across various image recognition applications. Convolutional Neural Networks (CNNs), which have been successful in many computer vision tasks, are…

Contrastive Language-Image Pretraining (CLIP) has achieved remarkable success, leading to rapid advancements in multimodal studies. However, CLIP faces a notable challenge in terms of inefficient data utilization. It relies on a single…

Vision-language models (VLMs) extend the conventional large language models by integrating visual data, enabling richer multimodal reasoning and significantly broadens the practical applications of AI. However, including visual inputs also…

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-Language (VL) models have garnered considerable research interest; however, they still face challenges in effectively handling text within images. To address this limitation, researchers have developed two approaches. The first…

Vision-Language Pre-training (VLP) shows remarkable progress with the assistance of extremely heavy parameters, which challenges deployment in real applications. Knowledge distillation is well recognized as the essential procedure in model…

This paper presents a comprehensive survey of vision-language (VL) intelligence from the perspective of time. This survey is inspired by the remarkable progress in both computer vision and natural language processing, and recent trends…

Vision-Language Models (VLMs) leverage aligned visual encoders to transform images into visual tokens, allowing them to be processed similarly to text by the backbone large language model (LLM). This unified input paradigm enables VLMs to…

Vision Transformers (ViTs) is emerging as an alternative to convolutional neural networks (CNNs) for visual recognition. They achieve competitive results with CNNs but the lack of the typical convolutional inductive bias makes them more…

Vision Transformers (ViTs) enabled the use of the transformer architecture on vision tasks showing impressive performances when trained on big datasets. However, on relatively small datasets, ViTs are less accurate given their lack of…

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…