# EATFormer: Improving Vision Transformer Inspired by Evolutionary Algorithm

arXiv: https://arxiv.org/abs/2206.09325 · HTML: https://mlsanity.com/paper/2206.09325/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 115 of its 162 references that are in the map.
- First posted on arXiv 19 Jun 2022.

## Builds on (most cited first, 30 of 115)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Reformer: The Efficient Transformer](https://mlsanity.com/paper/2001.04451/) (2020)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Rethinking Attention with Performers](https://mlsanity.com/paper/2009.14794/) (2020)
- [TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation](https://mlsanity.com/paper/2102.04306/) (2021)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)

## Built on by (most cited first, 27 of 27)

- [MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection](https://mlsanity.com/paper/2404.06564/) (2024)
- [Deepfake Generation and Detection: A Benchmark and Survey](https://mlsanity.com/paper/2403.17881/) (2024)
- [CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detection](https://mlsanity.com/paper/2311.00453/) (2023)
- [Towards Robust Referring Image Segmentation](https://mlsanity.com/paper/2209.09554/) (2022)
- [Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detection](https://mlsanity.com/paper/2312.07495/) (2023)
- [Rethinking Mobile Block for Efficient Attention-based Models](https://mlsanity.com/paper/2301.01146/) (2023)
- [DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection](https://mlsanity.com/paper/2312.06607/) (2023)
- [PanopticPartFormer++: A Unified and Decoupled View for Panoptic Part Segmentation](https://mlsanity.com/paper/2301.00954/) (2023)
- [Learning Feature Inversion for Multi-class Anomaly Detection under General-purpose COCO-AD Benchmark](https://mlsanity.com/paper/2404.10760/) (2024)
- [B2Opt: Learning to Optimize Black-box Optimization with Little Budget](https://mlsanity.com/paper/2304.11787/) (2023)
- [Reference Twice: A Simple and Unified Baseline for Few-Shot Instance Segmentation](https://mlsanity.com/paper/2301.01156/) (2023)
- [JOTR: 3D Joint Contrastive Learning with Transformers for Occluded Human Mesh Recovery](https://mlsanity.com/paper/2307.16377/) (2023)
- [CAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient Mobile Applications](https://mlsanity.com/paper/2408.03703/) (2024)
- [PVG: Progressive Vision Graph for Vision Recognition](https://mlsanity.com/paper/2308.00574/) (2023)
- [Toward High Quality Facial Representation Learning](https://mlsanity.com/paper/2309.03575/) (2023)
- [Better "CMOS" Produces Clearer Images: Learning Space-Variant Blur Estimation for Blind Image Super-Resolution](https://mlsanity.com/paper/2304.03542/) (2023)
- [A Comprehensive Library for Benchmarking Multi-class Visual Anomaly Detection](https://mlsanity.com/paper/2406.03262/) (2024)
- [Learning Global-aware Kernel for Image Harmonization](https://mlsanity.com/paper/2305.11676/) (2023)
- [SoftHGNN: Soft Hypergraph Neural Networks for General Visual Recognition](https://mlsanity.com/paper/2505.15325/) (2025)
- [Iterative Robust Visual Grounding with Masked Reference based Centerpoint Supervision](https://mlsanity.com/paper/2307.12392/) (2023)
- [Depth Matters: Exploring Deep Interactions of RGB-D for Semantic Segmentation in Traffic Scenes](https://mlsanity.com/paper/2409.07995/) (2024)
- [Exploiting Lightweight Hierarchical ViT and Dynamic Framework for Efficient Visual Tracking](https://mlsanity.com/paper/2506.20381/) (2025)
- [Convolution-enhanced Evolving Attention Networks](https://mlsanity.com/paper/2212.08330/) (2022)
- [EViT: An Eagle Vision Transformer with Bi-Fovea Self-Attention](https://mlsanity.com/paper/2310.06629/) (2023)
- [Improved EATFormer: A Vision Transformer for Medical Image Classification](https://mlsanity.com/paper/2403.13167/) (2024)
- [Adaptive Blind Super-Resolution Network for Spatial-Specific and Spatial-Agnostic Degradations](https://mlsanity.com/paper/2506.07705/) (2025)
- [Revolutionizing Traffic Sign Recognition: Unveiling the Potential of Vision Transformers](https://mlsanity.com/paper/2404.19066/) (2024)

## Abstract (arXiv)

Motivated by biological evolution, this paper explains the rationality of Vision Transformer by analogy with the proven practical evolutionary algorithm (EA) and derives that both have consistent mathematical formulation. Then inspired by effective EA variants, we propose a novel pyramid EATFormer backbone that only contains the proposed EA-based transformer (EAT) block, which consists of three residual parts, i.e., Multi-scale region aggregation, global and local interaction, and feed-forward network modules, to model multi-scale, interactive, and individual information separately. Moreover, we design a task-related head docked with transformer backbone to complete final information fusion more flexibly and improve a modulated deformable MSA to dynamically model irregular locations. Massive quantitative and quantitative experiments on image classification, downstream tasks, and explanatory experiments demonstrate the effectiveness and superiority of our approach over state-of-the-art methods. E.g., our Mobile (1.8 M), Tiny (6.1 M), Small (24.3 M), and Base (49.0 M) models achieve 69.4, 78.4, 83.1, and 83.9 Top-1 only trained on ImageNet-1K with naive training recipe; EATFormer-Tiny/Small/Base armed Mask-R-CNN obtain 45.4/47.4/49.0 box AP and 41.4/42.9/44.2 mask AP on COCO detection, surpassing contemporary MPViT-T, Swin-T, and Swin-S by 0.6/1.4/0.5 box AP and 0.4/1.3/0.9 mask AP separately with less FLOPs; Our EATFormer-Small/Base achieve 47.3/49.3 mIoU on ADE20K by Upernet that exceeds Swin-T/S by 2.8/1.7. Code is available at https://github.com/zhangzjn/EATFormer.