相关论文: SVD-ViT: Does SVD Make Vision Transformers Attend …

Vision transformer (ViT) and its variants have swept through visual learning leaderboards and offer state-of-the-art accuracy in tasks such as image classification, object detection, and semantic segmentation by attending to different parts…

In this paper, we question if well pre-trained vision transformer (ViT) models could be used as teachers that exhibit scalable properties to advance cross architecture knowledge distillation (KD) research, in the context of using…

Pretrained vision foundation models deliver strong performance across tasks with limited fine-tuning. However, their Vision Transformer (ViT) backbones impose high inference costs, limiting deployment on resource-constrained devices. In…

The Principal Component Analysis (PCA) method and the Singular Value Decomposition (SVD) method are widely used for foreground subtraction in 21 cm intensity mapping experiments. We show their equivalence, and point out that the condition…

Previous works on multi-label image recognition (MLIR) usually use CNNs as a starting point for research. In this paper, we take pure Vision Transformer (ViT) as the research base and make full use of the advantages of Transformer with…

SVD (singular value decomposition) is one of the basic tools of machine learning, allowing to optimize basis for a given matrix. However, sometimes we have a set of matrices $\{A_k\}_k$ instead, and would like to optimize a single common…

The deep image prior (DIP) is a well-established unsupervised deep learning method for image reconstruction; yet it is far from being flawless. The DIP overfits to noise if not early stopped, or optimized via a regularized objective. We…

Semantic information has been proved effective in scene text recognition. Most existing methods tend to couple both visual and semantic information in an attention-based decoder. As a result, the learning of semantic features is prone to…

The large pre-trained vision transformers (ViTs) have demonstrated remarkable performance on various visual tasks, but suffer from expensive computational and memory cost problems when deployed on resource-constrained devices. Among the…

Roadside perception can greatly increase the safety of autonomous vehicles by extending their perception ability beyond the visual range and addressing blind spots. However, current state-of-the-art vision-based roadside detection methods…

The most recent year has witnessed the success of applying the Vision Transformer (ViT) for image classification. However, there are still evidences indicating that ViT often suffers following two aspects, i) the high computation and the…

Vision Transformer (ViT) architectures traditionally employ a grid-based approach to tokenization independent of the semantic content of an image. We propose a modular superpixel tokenization strategy which decouples tokenization and…

Vision transformers (ViTs) quantization offers a promising prospect to facilitate deploying large pre-trained networks on resource-limited devices. Fully-binarized ViTs (Bi-ViT) that pushes the quantization of ViTs to its limit remain…

Monocular depth estimation is a central problem in computer vision with applications in robotics, AR, and autonomous driving, yet the self-attention mechanisms that drive modern Transformer architectures remain opaque. We introduce…

Vision Transformers (ViTs), with their ability to model long-range dependencies through self-attention mechanisms, have become a standard architecture in computer vision. However, the interpretability of these models remains a challenge. To…

We present pure-transformer based models for video classification, drawing upon the recent success of such models in image classification. Our model extracts spatio-temporal tokens from the input video, which are then encoded by a series of…

Vision Transformers trained only on image classification routinely transfer to tasks that demand spatial understanding, yet they receive no spatial supervision during pretraining. We ask where and how robustly such structure is encoded.…

Following the success in advancing natural language processing and understanding, transformers are expected to bring revolutionary changes to computer vision. This work provides a comprehensive study on the robustness of vision transformers…

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…

Vision Transformers (ViTs) often degrade under distribution shifts because they rely on spurious correlations, such as background cues, rather than semantically meaningful features. Existing regularization methods, typically relying on…