Related papers: Scaling Laws in Patchification: An Image Is Worth …

Attention-based neural networks such as the Vision Transformer (ViT) have recently attained state-of-the-art results on many computer vision benchmarks. Scale is a primary ingredient in attaining excellent results, therefore, understanding…

Vision Transformer (ViT) has emerged as a powerful architecture in the realm of modern computer vision. However, its application in certain imaging fields, such as microscopy and satellite imaging, presents unique challenges. In these…

The vision transformer splits each image into a sequence of tokens with fixed length and processes the tokens in the same way as words in natural language processing. More tokens normally lead to better performance but considerably…

Vision Transformers (ViTs) and their variants have become state-of-the-art in many computer vision tasks and are widely used as backbones in large-scale vision and vision-language foundation models. While substantial research has focused on…

The vision transformer is a model that breaks down each image into a sequence of tokens with a fixed length and processes them similarly to words in natural language processing. Although increasing the number of tokens typically results in…

The recently proposed Visual image Transformers (ViT) with pure attention have achieved promising performance on image recognition tasks, such as image classification. However, the routine of the current ViT model is to maintain a…

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) are built on the assumption of treating image patches as ``visual tokens" and learn patch-to-patch attention. The patch embedding based tokenizer has a semantic gap with respect to its counterpart, the textual…

This paper studies the efficiency problem for visual transformers by excavating redundant calculation in given networks. The recent transformer architecture has demonstrated its effectiveness for achieving excellent performance on a series…

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…

Vision Transformers (ViTs) have emerged as the state-of-the-art architecture in representation learning, leveraging self-attention mechanisms to excel in various tasks. ViTs split images into fixed-size patches, constraining them to a…

This paper investigates the fundamental relationship between model capacity and the minimal number of visual tokens required to preserve image semantics. Inspired by the Minimum Description Length principle, we reinterpret image tokens as…

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 convert images to sequences by slicing them into patches. The size of these patches controls a speed/accuracy tradeoff, with smaller patches leading to higher accuracy at greater computational cost, but changing the…

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…

Vision Transformer models process input images by dividing them into a spatially regular grid of equal-size patches. Conversely, Transformers were originally introduced over natural language sequences, where each token represents a subword…

Vision Transformers (ViTs) partition input images into uniformly sized patches regardless of their content, resulting in long input sequence lengths for high-resolution images. We present Adaptive Patch Transformers (APT), which addresses…

Quantization scale and bit-width are the most important parameters when considering how to quantize a neural network. Prior work focuses on optimizing quantization scales in a global manner through gradient methods (gradient descent \&…

Vision Transformers (ViTs) have achieved remarkable performance in various image classification tasks by leveraging the attention mechanism to process image patches as tokens. However, the high computational and memory demands of ViTs pose…

The capacity of Vision transformers (ViTs) to handle variable-sized inputs is often constrained by computational complexity and batch processing limitations. Consequently, ViTs are typically trained on small, fixed-size images obtained…