相关论文: Leveraging Registers in Vision Transformers for Ro…

Vision Transformers (ViTs) have emerged as the dominant architecture for visual processing tasks, demonstrating excellent scalability with increased training data and model size. However, recent work has identified the emergence of artifact…

Vision Transformers (ViTs) are known to exhibit high-norm patch-token outliers that degrade feature map quality, a problem effectively mitigated by \textit{register tokens}. As diffusion models increasingly adopt transformer architectures…

Vision Transformer (ViT) is emerging as the state-of-the-art architecture for image recognition. While recent studies suggest that ViTs are more robust than their convolutional counterparts, our experiments find that ViTs trained on…

Transformers have recently emerged as a powerful tool for learning visual representations. In this paper, we identify and characterize artifacts in feature maps of both supervised and self-supervised ViT networks. The artifacts correspond…

Drawing inspiration from recent findings including surprisingly decent performance of transformers without positional encoding (NoPE) in the domain of language models and how registers (additional throwaway tokens not tied to input) may…

Training Vision Transformers (ViTs) presents significant challenges, one of which is the emergence of artifacts in attention maps, hindering their interpretability. Darcet et al. (2024) investigated this phenomenon and attributed it to the…

Vision Transformers (ViTs), when pre-trained on large-scale data, provide general-purpose representations for diverse downstream tasks. However, artifacts in ViTs are widely observed across different supervision paradigms and downstream…

Recent work has shown that the attention maps of the widely popular DINOv2 model exhibit artifacts, which hurt both model interpretability and performance on dense image tasks. These artifacts emerge due to the model repurposing patch…

Vision Transformers (ViTs) have successfully been applied to image classification problems where large annotated datasets are available. On the other hand, when fewer annotations are available, such as in biomedical applications, image…

Recent advancements in vision-language models (VLMs) have expanded their potential for real-world applications, enabling these models to perform complex reasoning on images. In the widely used fully autoregressive transformer-based models…

Vision Transformer (ViT) architectures represent images as collections of high-dimensional vectorized tokens, each corresponding to a rectangular non-overlapping patch. This representation trades spatial granularity for embedding…

Vision Transformers (ViTs) have demonstrated superior performance across a wide range of computer vision tasks. However, structured noise artifacts in their feature maps hinder downstream applications such as segmentation and depth…

We investigate the mechanism underlying a previously identified phenomenon in Vision Transformers - the emergence of high-norm tokens that lead to noisy attention maps (Darcet et al., 2024). We observe that in multiple models (e.g., CLIP,…

Vision transformers (ViTs) have demonstrated remarkable performance in a variety of vision tasks. Despite their promising capabilities, training a ViT requires a large amount of diverse data. Several studies empirically found that using…

We investigate the robustness of vision transformers (ViTs) through the lens of their special patch-based architectural structure, i.e., they process an image as a sequence of image patches. We find that ViTs are surprisingly insensitive to…

We study outlier tokens in Diffusion Transformers (DiTs) for image generation. Prior work has shown that Vision Transformers (ViTs) can produce a small number of high-norm tokens that attract disproportionate attention while carrying…

In this paper, we present token labeling -- a new training objective for training high-performance vision transformers (ViTs). Different from the standard training objective of ViTs that computes the classification loss on an additional…

Vision transformers (ViTs) achieve remarkable performance on large datasets, but tend to perform worse than convolutional neural networks (CNNs) when trained from scratch on smaller datasets, possibly due to a lack of local inductive bias…

Vision Transformers (ViTs) have recently dominated a range of computer vision tasks, yet it suffers from low training data efficiency and inferior local semantic representation capability without appropriate inductive bias. Convolutional…

Vision Transformer (ViT) and its variants (e.g., Swin, PVT) have achieved great success in various computer vision tasks, owing to their capability to learn long-range contextual information. Layer Normalization (LN) is an essential…