mlsanityData to 7 Oct 2026

Regularized Evolution for Image Classifier Architecture Search

arXiv 1802.01548 ↗First posted 5 Feb 2018cs.NE cs.AI cs.CVcited by 902

Not on the map. Why?

Cited by 20 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The effort devoted to hand-crafting neural network image classifiers has motivated the use of architecture search to discover them automatically. Although evolutionary algorithms have been repeatedly applied to neural network topologies, the image classifiers thus discovered have remained inferior to human-crafted ones. Here, we evolve an image classifier---AmoebaNet-A---that surpasses hand-designs for the first time. To do this, we modify the tournament selection evolutionary algorithm by introducing an age property to favor the younger genotypes. Matching size, AmoebaNet-A has comparable accuracy to current state-of-the-art ImageNet models discovered with more complex architecture-search methods. Scaled to larger size, AmoebaNet-A sets a new state-of-the-art 83.9% / 96.6% top-5 ImageNet accuracy. In a controlled comparison against a well known reinforcement learning algorithm, we give evidence that evolution can obtain results faster with the same hardware, especially at the earlier stages of the search. This is relevant when fewer compute resources are available. Evolution is, thus, a simple method to effectively discover high-quality architectures.

Key facts. Cited by 902 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 1; 2019: 0; 2020: 0; 2021: 305; 2022: 189; 2023: 133; 2024: 104; 2025: 92; 2026: 78.

902 papers.

Sort:

By area:

  1. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 520
  2. 2023Symbolic Discovery of Optimization Algorithmscited by 423
  3. 2021ResNet strikes back: An improved training procedure in timmcited by 365
  4. 2021True Few-Shot Learning with Language Modelscited by 343
  5. 2021Coordinate Attention for Efficient Mobile Network Designcited by 239
  6. 2025AIDE: AI-Driven Exploration in the Space of Codecited by 206
  7. 2021Zero-Cost Proxies for Lightweight NAScited by 194
  8. 2021AutoFormer: Searching Transformers for Visual Recognitioncited by 186
  9. 2021Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspectivecited by 168
  10. 2021Primer: Searching for Efficient Transformers for Language Modelingcited by 162
  11. 2022Compute Trends Across Three Eras of Machine Learningcited by 161
  12. 2021Revisiting ResNets: Improved Training and Scaling Strategiescited by 158
38 more
  1. 2021Embodied Intelligence via Learning and Evolutioncited by 154
  2. 2021Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Bettercited by 153
  3. 2021Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challengescited by 143
  4. 2023Neural Architecture Search: Insights from 1000 Paperscited by 136
  5. 2023EvoPrompting: Language Models for Code-Level Neural Architecture Searchcited by 129
  6. 2021Parallel Bayesian Optimization of Multiple Noisy Objectives with Expected Hypervolume Improvementcited by 115
  7. 2021A Survey of Modern Deep Learning based Object Detection Modelscited by 97
  8. 2021Rethinking Architecture Selection in Differentiable NAScited by 92
  9. 2021Parameter Prediction for Unseen Deep Architecturescited by 89
  10. 2021How Powerful are Performance Predictors in Neural Architecture Search?cited by 88
  11. 2021Do Transformer Modifications Transfer Across Implementations and Applications?cited by 87
  12. 2021Diverse Branch Block: Building a Convolution as an Inception-like Unitcited by 87
  13. 2021Sample and Computation Redistribution for Efficient Face Detectioncited by 86
  14. 2021LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Searchcited by 82
  15. 2022Towards Learning Universal Hyperparameter Optimizers with Transformerscited by 81
  16. 2023Full Stack Optimization of Transformer Inference: a Surveycited by 79
  17. 2023MatFormer: Nested Transformer for Elastic Inferencecited by 79
  18. 2021MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edgecited by 77
  19. 2024AutoFlow: Automated Workflow Generation for Large Language Model Agentscited by 76
  20. 2024Symbolic Regression with a Learned Concept Librarycited by 76
  21. 2021A Practical Survey on Faster and Lighter Transformerscited by 73
  22. 2021Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learningcited by 72
  23. 2021Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognitioncited by 71
  24. 2021Exploring Relational Context for Multi-Task Dense Predictioncited by 71
  25. 2023AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Accelerationcited by 70
  26. 2025RF-DETR: Neural Architecture Search for Real-Time Detection Transformerscited by 70
  27. 2022Automated Reinforcement Learning (AutoRL): A Survey and Open Problemscited by 69
  28. 2021Chimera: Efficiently Training Large-Scale Neural Networks with Bidirectional Pipelinescited by 68
  29. 2022Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Spacecited by 66
  30. 2025AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-benchcited by 65
  31. 2021BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Searchcited by 63
  32. 2022β-DARTS: Beta-Decay Regularization for Differentiable Architecture Searchcited by 63
  33. 2021Compute and Energy Consumption Trends in Deep Learning Inferencecited by 61
  34. 2023GPT4AIGChip: Towards Next-Generation AI Accelerator Design Automation via Large Language Modelscited by 59
  35. 2021TransNAS-Bench-101: Improving Transferability and Generalizability of Cross-Task Neural Architecture Searchcited by 57
  36. 2023ZiCo: Zero-shot NAS via Inverse Coefficient of Variation on Gradientscited by 57
  37. 2021Deep RGB-D Saliency Detection with Depth-Sensitive Attention and Automatic Multi-Modal Fusioncited by 56
  38. 2023How Simulation Helps Autonomous Driving:A Survey of Sim2real, Digital Twins, and Parallel Intelligencecited by 55

50 most cited of 902 All 902 (JSON)