相关论文: Registers Matter for Pixel-Space Diffusion Transfo…

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…

Vision Transformers (ViTs) have shown success across a variety of tasks due to their ability to capture global image representations. Recent studies have identified the existence of high-norm tokens in ViTs, which can interfere with…

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…

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 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…

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,…

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…

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…

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…

Vision Transformers (ViTs) can learn strong image-level representations while their patch representations become less effective for dense prediction during prolonged training. We revisit this dense degradation phenomenon and argue that it…

Diffusion Transformers (DiTs) introduce the transformer architecture to diffusion tasks for latent-space image generation. With an isotropic architecture that chains a series of transformer blocks, DiTs demonstrate competitive performance…

Vision transformers (ViTs) have achieved promising results on a variety of Computer Vision tasks, however their quadratic complexity in the number of input tokens has limited their application specially in resource-constrained settings.…

Transformers, which are popular for language modeling, have been explored for solving vision tasks recently, e.g., the Vision Transformer (ViT) for image classification. The ViT model splits each image into a sequence of tokens with fixed…

Recently, the tokens of images share the same static data flow in many dense networks. However, challenges arise from the variance among the objects in images, such as large variations in the spatial scale and difficulties of recognition…

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) process input images as sequences of patches via self-attention; a radically different architecture than convolutional neural networks (CNNs). This makes it interesting to study the adversarial feature space of…

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…

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 Transformer (ViT) has achieved remarkable success due to its large-scale pretraining on general domains, but it still faces challenges when applying it to downstream distant domains that have only scarce training data, which gives…

Vision-transformers (ViTs) and large-scale convolution-neural-networks (CNNs) have reshaped computer vision through pretrained feature representations that enable strong transfer learning for diverse tasks. However, their efficiency as…