Equivariant Transformer Networks

2019-01-25 · Kai Sheng Tai, Peter Bailis, Gregory Valiant

How can prior knowledge on the transformation invariances of a domain be incorporated into the architecture of a neural network? We propose Equivariant Transformers (ETs), a family of differentiable image-to-image mappings that improve the robustness of models towards pre-defined continuous transformation groups. Through the use of specially-derived canonical coordinate systems, ETs incorporate functions that are equivariant by construction with respect to these transformations. We show empirically that ETs can be flexibly composed to improve model robustness towards more complicated transformation groups in several parameters. On a real-world image classification task, ETs improve the sample efficiency of ResNet classifiers, achieving relative improvements in error rate of up to 15% in the limited data regime while increasing model parameter count by less than 1%.

📄 PDF Abstract BibTeX arXiv:1901.11399

Code (3)

stanford-futuredata/equivariant-transformers 공식 구현 pytorch

julianroth/equivariant-transformers tf

siddhantmittal7/GroupTransformEquivariance pytorch

Tasks

General Classification image-classification Image Classification

Methods 이 논문이 사용한 방법론

Average Pooling 설명 없음

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…

Batch Normalization 설명 없음

Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…

Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…

Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…

Kaiming Initialization 설명 없음

REViT: Roto-reflection Equivariant Convolutional Vision Transformer

2026-06-24 · Sheir A. Zaheer, Alexander C. Holston, Chan Y. Park arxiv

In this paper, we propose a discrete roto-reflection group equivariant vision transformer with convolutional attention. Roto-reflection equivariant networks preserve the rotational, flip and positional symmetry in featur…

Image Classification Object Detection

A Unified Framework for Vision Transformers Equivariant to Discrete Subgroups of $\mathrm{O}(2)$

2026-06-26 · Tīkun Ông, Georg Bökman arxiv

Vision transformers have become a dominant architecture for visual recognition. However, standard models do not explicitly encode the planar symmetries that arise in many vision domains. We introduce a family of vision t…

$E(2)$-Equivariant Vision Transformer

2023-06-11 · Renjun Xu, Kaifan Yang, Ke Liu, Fengxiang He

Vision Transformer (ViT) has achieved remarkable performance in computer vision. However, positional encoding in ViT makes it substantially difficult to learn the intrinsic equivariance in data. Initial attempts have bee…

Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs

2022-06-23 · Yi-Lun Liao, Tess Smidt

Despite their widespread success in various domains, Transformer networks have yet to perform well across datasets in the domain of 3D atomistic graphs such as molecules even when 3D-related inductive biases like transla…

Graph Attention Graph Neural Network Graph Property Prediction Initial Structure to Relaxed Energy (IS2RE), Direct+1

$SE(3)$ Equivariant Convolution and Transformer in Ray Space

2023-09-21

3D reconstruction and novel view rendering can greatly benefit from geometric priors when the input views are not sufficient in terms of coverage and inter-view baselines. Deep learning of geometric priors from 2D images…

3D Reconstruction Neural Rendering