相关论文: Token Pruning using a Lightweight Background Aware…

A surge of interest has emerged in utilizing Transformers in diverse vision tasks owing to its formidable performance. However, existing approaches primarily focus on optimizing internal model architecture designs that often entail…

In recent years, Transformers have achieved remarkable progress in computer vision tasks. However, their global modeling often comes with substantial computational overhead, in stark contrast to the human eye's efficient information…

Vision Transformers (ViTs) have demonstrated strong performance across a range of computer vision tasks by modeling long-range spatial interactions via self-attention. However, channel-wise mixing in ViTs remains static, relying on fixed…

Large Vision-Language Models (LVLMs) process multimodal inputs consisting of text tokens and vision tokens extracted from images or videos. Due to the rich visual information, a single image can generate thousands of vision tokens, leading…

Vision Large Language Models (VLLMs) incur high computational costs due to their reliance on hundreds of visual tokens to represent images. While token pruning offers a promising solution for accelerating inference, this paper, however,…

Vision Transformers have witnessed prevailing success in a series of vision tasks. However, these Transformers often rely on extensive computational costs to achieve high performance, which is burdensome to deploy on resource-constrained…

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…

Token pruning methods for Vision Transformers (ViTs) promise quadratic reductions in attention FLOPs by dropping uninformative patches. Yet standard variable-length attention APIs -- including FlashAttention-2's varlen and PyTorch's…

Vision-Language Models (VLMs) process thousands of visual tokens per image alongside comparatively few text tokens, yet existing compression methods treat both modalities uniformly. We observe that the two modalities have fundamentally…

Effective video tokenization is critical for scaling transformer models for long videos. Current approaches tokenize videos using space-time patches, leading to excessive tokens and computational inefficiencies. The best token reduction…

We design a family of image classification architectures that optimize the trade-off between accuracy and efficiency in a high-speed regime. Our work exploits recent findings in attention-based architectures, which are competitive on highly…

Light-weight convolutional neural networks (CNNs) are the de-facto for mobile vision tasks. Their spatial inductive biases allow them to learn representations with fewer parameters across different vision tasks. However, these networks are…

The paper proposes an efficient structure for enhancing the performance of mobile-friendly vision transformer with small computational overhead. The vision transformer (ViT) is very attractive in that it reaches outperforming results in…

This work aims to improve the efficiency of vision transformers (ViT). While ViTs use computationally expensive self-attention operations in every layer, we identify that these operations are highly correlated across layers -- a key…

Can a lightweight Vision Transformer (ViT) match or exceed the performance of Convolutional Neural Networks (CNNs) like ResNet on small datasets with small image resolutions? This report demonstrates that a pure ViT can indeed achieve…

Models for fine-grained image classification tasks, where the difference between some classes can be extremely subtle and the number of samples per class tends to be low, are particularly prone to picking up background-related biases and…

Recent multimodal large language models are computationally expensive because Transformers must process a large number of visual tokens. We present ReDiPrune, a training-free token pruning method applied before the vision-language…

Intermediate features of a pre-trained model have been shown informative for making accurate predictions on downstream tasks, even if the model backbone is kept frozen. The key challenge is how to utilize these intermediate features given…

Vision Transformers (ViTs) have achieved state-of-the-art performance on various vision tasks. However, ViTs' self-attention module is still arguably a major bottleneck, limiting their achievable hardware efficiency. Meanwhile, existing…

We present Region-aware Open-vocabulary Vision Transformers (RO-ViT) - a contrastive image-text pretraining recipe to bridge the gap between image-level pretraining and open-vocabulary object detection. At the pretraining phase, we propose…