Low-latency vision transformers via large-scale multi-head attention

• URL: http://arxiv.org/abs/2506.23832v1
• Date: Mon, 30 Jun 2025 13:23:46 GMT
• Title: Low-latency vision transformers via large-scale multi-head attention
• Authors: Ronit D. Gross, Tal Halevi, Ella Koresh, Yarden Tzach, Ido Kanter,
• Abstract summary: A learning mechanism is generalized to large-scale MHA (LS-MHA) using a single matrix value representing single-head performance.<n>Several distinct vision transformer (ViT) architectures achieve the same accuracy but differ in their LS-MHA structures.<n>The extension of this learning mechanism to natural language processing tasks has the potential to yield new insights in deep learning.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The emergence of spontaneous symmetry breaking among a few heads of multi-head attention (MHA) across transformer blocks in classification tasks was recently demonstrated through the quantification of single-nodal performance (SNP). This finding indicates that each head focuses its attention on a subset of labels through cooperation among its SNPs. This underlying learning mechanism is generalized to large-scale MHA (LS-MHA) using a single matrix value representing single-head performance (SHP), analogous to single-filter performance in convolutional neural networks (CNNs). The results indicate that each SHP matrix comprises multiple unit clusters such that each label being explicitly recognized by a few heads with negligible noise. This leads to an increased signal-to-noise ratio (SNR) along the transformer blocks, thereby improving classification accuracy. These features give rise to several distinct vision transformer (ViT) architectures that achieve the same accuracy but differ in their LS-MHA structures. As a result, their soft committee yields superior accuracy, an outcome not typically observed in CNNs which rely on hundreds of filters. In addition, a significant reduction in latency is achieved without affecting the accuracy by replacing the initial transformer blocks with convolutional layers. This substitution accelerates early-stage learning, which is then improved by subsequent transformer layers. The extension of this learning mechanism to natural language processing tasks, based on quantitative differences between CNNs and ViT architectures, has the potential to yield new insights in deep learning. The findings are demonstrated using compact convolutional transformer architectures trained on the CIFAR-100 dataset.

Related papers

• Small transformer architectures for task switching [2.7195102129095003]
  It is non-trivial to conceive small-scale applications for which attention-based architectures outperform traditional approaches.<n>We show that standard transformers cannot solve a basic task switching reference model.<n>We show that transformers, long short-term memory recurrent networks (LSTM), and plain multi-layer perceptrons (MLPs) achieve similar, but only modest prediction accuracies.
  arXiv  Detail & Related papers  (2025-08-06T14:01:05Z)
• Is Attention Required for Transformer Inference? Explore Function-preserving Attention Replacement [13.38679135071682]
  We propose a Function-preserving Attention Replacement framework that replaces all attention blocks in pretrained transformers with learnable sequence-to-sequence modules.<n>We validate FAR on the DeiT vision transformer family and demonstrate that it matches the accuracy of the original models on ImageNet and multiple downstream tasks with reduced parameters and latency.
  arXiv  Detail & Related papers  (2025-05-24T02:23:46Z)
• Transformer Meets Twicing: Harnessing Unattended Residual Information [2.1605931466490795]
  Transformer-based deep learning models have achieved state-of-the-art performance across numerous language and vision tasks.<n>While the self-attention mechanism has proven capable of handling complex data patterns, it has been observed that the representational capacity of the attention matrix degrades significantly across transformer layers.<n>We propose the Twicing Attention, a novel attention mechanism that uses kernel twicing procedure in nonparametric regression to alleviate the low-pass behavior of associated NLM smoothing.
  arXiv  Detail & Related papers  (2025-03-02T01:56:35Z)
• Unified CNNs and transformers underlying learning mechanism reveals multi-head attention modus vivendi [0.0]
  Convolutional neural networks (CNNs) evaluate short-range correlations in input images which progress along the layers.<n> vision transformer (ViT) architectures evaluate long-range correlations, using repeated transformer encoders composed of fully connected layers.<n>This study demonstrates that CNNs and ViT architectures stem from a unified underlying learning mechanism.
  arXiv  Detail & Related papers  (2025-01-22T14:19:48Z)
• Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers [54.20763128054692]
  We study how a two-attention-layer transformer is trained to perform ICL on $n$-gram Markov chain data. We prove that the gradient flow with respect to a cross-entropy ICL loss converges to a limiting model.
  arXiv  Detail & Related papers  (2024-09-09T18:10:26Z)
• Rich CNN-Transformer Feature Aggregation Networks for Super-Resolution [50.10987776141901]
  Recent vision transformers along with self-attention have achieved promising results on various computer vision tasks. We introduce an effective hybrid architecture for super-resolution (SR) tasks, which leverages local features from CNNs and long-range dependencies captured by transformers. Our proposed method achieves state-of-the-art SR results on numerous benchmark datasets.
  arXiv  Detail & Related papers  (2022-03-15T06:52:25Z)
• Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstruction [138.04956118993934]
  We propose a novel Transformer-based method, coarse-to-fine sparse Transformer (CST) CST embedding HSI sparsity into deep learning for HSI reconstruction. In particular, CST uses our proposed spectra-aware screening mechanism (SASM) for coarse patch selecting. Then the selected patches are fed into our customized spectra-aggregation hashing multi-head self-attention (SAH-MSA) for fine pixel clustering and self-similarity capturing.
  arXiv  Detail & Related papers  (2022-03-09T16:17:47Z)
• CSformer: Bridging Convolution and Transformer for Compressive Sensing [65.22377493627687]
  This paper proposes a hybrid framework that integrates the advantages of leveraging detailed spatial information from CNN and the global context provided by transformer for enhanced representation learning. The proposed approach is an end-to-end compressive image sensing method, composed of adaptive sampling and recovery. The experimental results demonstrate the effectiveness of the dedicated transformer-based architecture for compressive sensing.
  arXiv  Detail & Related papers  (2021-12-31T04:37:11Z)
• Vision Transformers with Hierarchical Attention [61.16912607330001]
  This paper tackles the high computational/space complexity associated with Multi-Head Self-Attention (MHSA) in vision transformers. We propose Hierarchical MHSA (H-MHSA), a novel approach that computes self-attention in a hierarchical fashion. We build a family of Hierarchical-Attention-based Transformer Networks, namely HAT-Net.
  arXiv  Detail & Related papers  (2021-06-06T17:01:13Z)
• Less is More: Pay Less Attention in Vision Transformers [61.05787583247392]
  Less attention vIsion Transformer builds upon the fact that convolutions, fully-connected layers, and self-attentions have almost equivalent mathematical expressions for processing image patch sequences. The proposed LIT achieves promising performance on image recognition tasks, including image classification, object detection and instance segmentation.
  arXiv  Detail & Related papers  (2021-05-29T05:26:07Z)
• Understanding Self-supervised Learning with Dual Deep Networks [74.92916579635336]
  We propose a novel framework to understand contrastive self-supervised learning (SSL) methods that employ dual pairs of deep ReLU networks. We prove that in each SGD update of SimCLR with various loss functions, the weights at each layer are updated by a emphcovariance operator. To further study what role the covariance operator plays and which features are learned in such a process, we model data generation and augmentation processes through a emphhierarchical latent tree model (HLTM)
  arXiv  Detail & Related papers  (2020-10-01T17:51:49Z)
• Self-grouping Convolutional Neural Networks [30.732298624941738]
  We propose a novel method of designing self-grouping convolutional neural networks, called SG-CNN. For each filter, we first evaluate the importance value of their input channels to identify the importance vectors. Using the resulting emphdata-dependent centroids, we prune the less important connections, which implicitly minimizes the accuracy loss of the pruning.
  arXiv  Detail & Related papers  (2020-09-29T06:24:32Z)
• Sequential Hierarchical Learning with Distribution Transformation for Image Super-Resolution [83.70890515772456]
  We build a sequential hierarchical learning super-resolution network (SHSR) for effective image SR. We consider the inter-scale correlations of features, and devise a sequential multi-scale block (SMB) to progressively explore the hierarchical information. Experiment results show SHSR achieves superior quantitative performance and visual quality to state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-07-19T01:35:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.