mlsanityData to 14 Oct 2026

CARS: Continuous Evolution for Efficient Neural Architecture Search

arXiv 1909.04977 ↗First posted 11 Sep 2019cs.CVcited by 79

Not on the map. Why?

Abstract (arXiv)

Searching techniques in most of existing neural architecture search (NAS) algorithms are mainly dominated by differentiable methods for the efficiency reason. In contrast, we develop an efficient continuous evolutionary approach for searching neural networks. Architectures in the population that share parameters within one SuperNet in the latest generation will be tuned over the training dataset with a few epochs. The searching in the next evolution generation will directly inherit both the SuperNet and the population, which accelerates the optimal network generation. The non-dominated sorting strategy is further applied to preserve only results on the Pareto front for accurately updating the SuperNet. Several neural networks with different model sizes and performances will be produced after the continuous search with only 0.4 GPU days. As a result, our framework provides a series of networks with the number of parameters ranging from 3.7M to 5.1M under mobile settings. These networks surpass those produced by the state-of-the-art methods on the benchmark ImageNet dataset.

Key facts. Cited by 79 papers in the map (data through 14 Oct 2026). First posted on arXiv 11 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 27; 2022: 20; 2023: 8; 2024: 12; 2025: 7; 2026: 5.

79 papers.

Sort:

By area:

  1. 2022Vision GNN: An Image is Worth Graph of Nodescited by 186
  2. 2021Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspectivecited by 169
  3. 2021Distilling Object Detectors via Decoupled Featurescited by 106
  4. 2021Parameter Prediction for Unseen Deep Architecturescited by 89
  5. 2021Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognitioncited by 73
  6. 2023ZiCo: Zero-shot NAS via Inverse Coefficient of Variation on Gradientscited by 58
  7. 2021Combined Depth Space based Architecture Search For Person Re-identificationcited by 44
  8. 2021Manifold Regularized Dynamic Network Pruningcited by 43
  9. 2025Scaling Image and Video Generation via Test-Time Evolutionary Searchcited by 40
  10. 2021Stronger NAS with Weaker Predictorscited by 28
  11. 2024AZ-NAS: Assembling Zero-Cost Proxies for Network Architecture Searchcited by 28
  12. 2021BN-NAS: Neural Architecture Search with Batch Normalizationcited by 21
38 more
  1. 2021Analogous to Evolutionary Algorithm: Designing a Unified Sequence Modelcited by 20
  2. 2021Analyzing and Mitigating Interference in Neural Architecture Searchcited by 20
  3. 2022Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolutioncited by 20
  4. 2022OPQ: Compressing Deep Neural Networks with One-shot Pruning-Quantizationcited by 19
  5. 2021Searching by Generating: Flexible and Efficient One-Shot NAS with Architecture Generatorcited by 15
  6. 2022GhostNets on Heterogeneous Devices via Cheap Operationscited by 15
  7. 2022EZNAS: Evolving Zero Cost Proxies For Neural Architecture Scoringcited by 15
  8. 2021BiX-NAS: Searching Efficient Bi-directional Architecture for Medical Image Segmentationcited by 13
  9. 2021Neural Architecture Dilation for Adversarial Robustnesscited by 13
  10. 2022DropNAS: Grouped Operation Dropout for Differentiable Architecture Searchcited by 12
  11. 2022A Survey on Computationally Efficient Neural Architecture Searchcited by 12
  12. 2021Multi-objective Search of Robust Neural Architectures against Multiple Types of Adversarial Attackscited by 11
  13. 2024SWAP-NAS: Sample-Wise Activation Patterns for Ultra-fast NAScited by 11
  14. 2021Accelerating Evolutionary Neural Architecture Search via Multi-Fidelity Evaluationcited by 10
  15. 2021EEEA-Net: An Early Exit Evolutionary Neural Architecture Searchcited by 9
  16. 2021GhostSR: Learning Ghost Features for Efficient Image Super-Resolutioncited by 8
  17. 2021FL-AGCNS: Federated Learning Framework for Automatic Graph Convolutional Network Searchcited by 8
  18. 2022PRE-NAS: Predictor-assisted Evolutionary Neural Architecture Searchcited by 8
  19. 2021Fisher Task Distance and Its Application in Neural Architecture Searchcited by 7
  20. 2021Pareto-wise Ranking Classifier for Multi-objective Evolutionary Neural Architecture Searchcited by 7
  21. 2022Partial Connection Based on Channel Attention for Differentiable Neural Architecture Searchcited by 7
  22. 2021Single-path Bit Sharing for Automatic Loss-aware Model Compressioncited by 6
  23. 2023Towards On-device Learning on the Edge: Ways to Select Neurons to Update under a Budget Constraintcited by 6
  24. 2021Evolutionary Multi-objective Architecture Search Framework: Application to COVID-19 3D CT Classificationcited by 5
  25. 2021Contrastive Self-supervised Neural Architecture Searchcited by 5
  26. 2021EAGAN: Efficient Two-stage Evolutionary Architecture Search for GANscited by 5
  27. 2022CLOSE: Curriculum Learning On the Sharing Extent Towards Better One-shot NAScited by 5
  28. 2024Investigating Calibration and Corruption Robustness of Post-hoc Pruned Perception CNNs: An Image Classification Benchmark Studycited by 5
  29. 2022Exploring the Intersection between Neural Architecture Search and Continual Learningcited by 4
  30. 2023Multiobjective Evolutionary Pruning of Deep Neural Networks with Transfer Learning for improving their Performance and Robustnesscited by 4
  31. 2023MathNAS: If Blocks Have a Role in Mathematical Architecture Designcited by 4
  32. 2022Towards Bi-directional Skip Connections in Encoder-Decoder Architectures and Beyondcited by 3
  33. 2022Bi-fidelity Evolutionary Multiobjective Search for Adversarially Robust Deep Neural Architecturescited by 3
  34. 2022Multi-Agent Automated Machine Learningcited by 3
  35. 2025Training-free Neural Architecture Search through Variance of Knowledge of Deep Network Weightscited by 3
  36. 2024Multi-Objective Evolutionary Neural Architecture Search for Recurrent Neural Networkscited by 2
  37. 2024A Pairwise Comparison Relation-assisted Multi-objective Evolutionary Neural Architecture Search Method with Multi-population Mechanismcited by 2
  38. 2021Across-Task Neural Architecture Search via Meta Learningcited by 1

50 most cited of 79 All 79 (JSON)