paper-with-me

홈 › Papers

Structured Initialization for Attention in Vision Transformers

2024-04-01 · Jianqiao Zheng, Xueqian Li, Simon Lucey

The training of vision transformer (ViT) networks on small-scale datasets poses a significant challenge. By contrast, convolutional neural networks (CNNs) have an architectural inductive bias enabling them to perform well on such problems. In this paper, we argue that the architectural bias inherent to CNNs can be reinterpreted as an initialization bias within ViT. This insight is significant as it empowers ViTs to perform equally well on small-scale problems while maintaining their flexibility for large-scale applications. Our inspiration for this ``structured'' initialization stems from our empirical observation that random impulse filters can achieve comparable performance to learned filters within CNNs. Our approach achieves state-of-the-art performance for data-efficient ViT learning across numerous benchmarks including CIFAR-10, CIFAR-100, and SVHN.

📄 PDF Abstract BibTeX arXiv:2404.01139

Code (1)

osiriszjq/structured_init 공식 구현 pytorch

Tasks

Inductive Bias

Methods 이 논문이 사용한 방법론

Attention 설명 없음
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 $x$…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Multi-Head Attention 설명 없음
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…
Vision Transformer The Vision Transformer, or ViT, is a model for image classification that employs a Transformer-like architecture over…

Similar Papers 제목 키워드 기반

Discrete Cosine Transform Based Decorrelated Attention for Vision Transformers

2024-05-22 · Hongyi Pan, Emadeldeen Hamdan, Xin Zhu, Ahmet Enis Cetin 외

Central to the Transformer architectures' effectiveness is the self-attention mechanism, a function that maps queries, keys, and values into a high-dimensional vector space. However, training the attention weights of que…

Quantization

Mask-Based Priors Are More Persistent than Query-Key Initializations

2026-08-01 · Mingze Ma, Hemanth Saratchandran, Cameron Gordon, Simon Lucey arxiv

Transformers do not merely lack data on some Boolean extrapolation tasks; they generalize in a systematically wrong way. Recent work on generalization on the unseen has shown that, despite fitting the observed domain, Tr…

Mimetic Initialization of Self-Attention Layers

2023-05-16 · Asher Trockman, J. Zico Kolter

It is notoriously difficult to train Transformers on small datasets; typically, large pre-trained models are instead used as the starting point. We explore the weights of such pre-trained Transformers (particularly for v…

Effective Theory of Transformers at Initialization

2023-04-04 · Emily Dinan, Sho Yaida, Susan Zhang

We perform an effective-theory analysis of forward-backward signal propagation in wide and deep Transformers, i.e., residual neural networks with multi-head self-attention blocks and multilayer perceptron blocks. This an…

Subcritical Signal Propagation at Initialization in Normalization-Free Transformers

2026-04-13 · Sergey Alekseev arxiv

We study signal propagation at initialization in transformers through the averaged partial Jacobian norm (APJN), a measure of gradient amplification across layers. We extend APJN analysis to transformers with bidirection…