paper-with-me

홈 › Papers

Unified CNNs and transformers underlying learning mechanism reveals multi-head attention modus vivendi

2025-01-22 · Ella Koresh, Ronit D. Gross, Yuval Meir, Yarden Tzach, Tal Halevi, Ido Kanter

Convolutional neural networks (CNNs) evaluate short-range correlations in input images which progress along the layers, whereas vision transformer (ViT) architectures evaluate long-range correlations, using repeated transformer encoders composed of fully connected layers. Both are designed to solve complex classification tasks but from different perspectives. This study demonstrates that CNNs and ViT architectures stem from a unified underlying learning mechanism, which quantitatively measures the single-nodal performance (SNP) of each node in feedforward (FF) and multi-head attention (MHA) subblocks. Each node identifies small clusters of possible output labels, with additional noise represented as labels outside these clusters. These features are progressively sharpened along the transformer encoders, enhancing the signal-to-noise ratio. This unified underlying learning mechanism leads to two main findings. First, it enables an efficient applied nodal diagonal connection (ANDC) pruning technique without affecting the accuracy. Second, based on the SNP, spontaneous symmetry breaking occurs among the MHA heads, such that each head focuses its attention on a subset of labels through cooperation among its SNPs. Consequently, each head becomes an expert in recognizing its designated labels, representing a quantitative MHA modus vivendi mechanism. These results are based on a compact convolutional transformer architecture trained on the CIFAR-100 and Flowers-102 datasets and call for their extension to other architectures and applications, such as natural language processing.

📄 PDF Abstract BibTeX arXiv:2501.12900

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Residual Connection 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Vision Transformer The Vision Transformer, or ViT, is a model for image classification that employs a Transformer-like architecture over…
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN

2022-05-27 · Siyuan Li, Di wu, Fang Wu, Zelin Zang 외

Masked image modeling, an emerging self-supervised pre-training method, has shown impressive success across numerous downstream vision tasks with Vision transformers. Its underlying idea is simple: a portion of the input…

Image ClassificationInstance SegmentationObject DetectionSelf-Supervised Image Classification+2

Are Transformers More Robust Than CNNs?

2021-11-10 · NeurIPS 2021 12 · Yutong Bai, Jieru Mei, Alan Yuille, Cihang Xie

Transformer emerges as a powerful tool for visual recognition. In addition to demonstrating competitive performance on a broad range of visual benchmarks, recent works also argue that Transformers are much more robust th…

Adversarial Robustness

Are Vision Transformers Robust to Spurious Correlations?

2022-03-17 · Soumya Suvra Ghosal, Yifei Ming, Yixuan Li

Deep neural networks may be susceptible to learning spurious correlations that hold on average but not in atypical test samples. As with the recent emergence of vision transformer (ViT) models, it remains underexplored h…

Unifying and Enhancing Graph Transformers via a Hierarchical Mask Framework

2025-10-21 · Yujie Xing, Xiao Wang, Bin Wu, Hai Huang 외 arxiv

Graph Transformers (GTs) have emerged as a powerful paradigm for graph representation learning due to their ability to model diverse node interactions. However, existing GTs often rely on intricate architectural designs …

Graph Representation Learning

A Unified Stochastic Mechanism Underlying Collective Behavior in Ants, Physical Systems, and Robotic Swarms

2025-11-08 · Lianhao Yin, Haiping Yu, Pascal Spino, Daniela Rus arxiv

Biological swarms, such as ant colonies, achieve collective goals through decentralized and stochastic individual behaviors. Similarly, physical systems composed of gases, liquids, and solids exhibit random particle moti…