Related papers: Softmax-free Linear Transformers
Vision transformers (ViT) have demonstrated impressive performance across various machine vision problems. These models are based on multi-head self-attention mechanisms that can flexibly attend to a sequence of image patches to encode…
Vision Transformers (ViTs) take all the image patches as tokens and construct multi-head self-attention (MHSA) among them. Complete leverage of these image tokens brings redundant computations since not all the tokens are attentive in MHSA.…
Vision Transformer (ViT) has made significant advancements in computer vision, thanks to its token mixer's sophisticated ability to capture global dependencies between all tokens. However, the quadratic growth in computational demands as…
Vision Transformer (ViT) has gained increasing attention in the computer vision community in recent years. However, the core component of ViT, Self-Attention, lacks explicit spatial priors and bears a quadratic computational complexity,…
Vision Transformers (ViTs) achieve state-of-the-art performance on challenging vision tasks, but their deployment on edge devices is severely hindered by the computational complexity and global reduction bottleneck imposed by layer…
The advent of Vision Transformers (ViTs) marks a substantial paradigm shift in the realm of computer vision. ViTs capture the global information of images through self-attention modules, which perform dot product computations among…
Post-training quantization (PTQ) has emerged as a promising solution for reducing the storage and computational cost of vision transformers (ViTs). Recent advances primarily target at crafting quantizers to deal with peculiar activations…
Since its introduction, softmax attention has become the backbone of modern transformer architectures due to its expressiveness and scalability across a wide range of tasks. However, the main drawback of softmax attention is the quadratic…
Vision Transformer(ViT) is now dominating many vision tasks. The drawback of quadratic complexity of its token-wise multi-head self-attention (MHSA), is extensively addressed via either token sparsification or dimension reduction (in…
Self-attention mechanisms, especially multi-head self-attention (MSA), have achieved great success in many fields such as computer vision and natural language processing. However, many existing vision transformer (ViT) works simply inherent…
At the core of the Transformer, the softmax normalizes the attention matrix to be right stochastic. Previous research has shown that this often de-stabilizes training and that enforcing the attention matrix to be doubly stochastic (through…
Vision Transformers (ViTs) are becoming more popular and dominating technique for various vision tasks, compare to Convolutional Neural Networks (CNNs). As a demanding technique in computer vision, ViTs have been successfully solved various…
The core for tackling the fine-grained visual categorization (FGVC) is to learn subtle yet discriminative features. Most previous works achieve this by explicitly selecting the discriminative parts or integrating the attention mechanism via…
While Transformer architecture excel at modeling long-range dependencies contributing to its widespread adoption in vision tasks the quadratic complexity of softmax-based attention mechanisms imposes a major bottleneck, particularly when…
Softmax is popular normalization method used in machine learning. Deep learning solutions like Transformer or BERT use the softmax function intensively, so it is worthwhile to optimize its performance. This article presents our methodology…
Recent Vision Transformer~(ViT) models have demonstrated encouraging results across various computer vision tasks, thanks to their competence in modeling long-range dependencies of image patches or tokens via self-attention. These models,…
Existing expressivity results for transformers typically rely on hardmax attention, high precision, and other architectural modifications that disconnect them from the models used in practice. We bridge this gap by analyzing standard…
Learning efficient and expressive visual representation has long been the pursuit of computer vision research. While Vision Transformers (ViTs) gradually replace traditional Convolutional Neural Networks (CNNs) as more scalable vision…
Standard softmax self-attention excels in vision tasks but incurs quadratic complexity O(N^2), limiting high-resolution deployment. Linear attention reduces the cost to O(N), yet its compressed state representations can impair modeling…
As the performance gains from accelerating quantized matrix multiplication plateau, the softmax operation becomes the critical bottleneck in Transformer inference. This bottleneck stems from two hardware limitations: (1) limited data…