Papers › Regularized Evolution for Image Classifier Architecture Search

Regularized Evolution for Image Classifier Architecture Search

5 Feb 2018arXiv:1802.01548archive 2025-07-28

Esteban Real, Alok Aggarwal, Yanping Huang, Quoc V. Le

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.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

tally0818/NASNet mentioned on GitHubpytorchSyntology: not harvested report
xuanhungho/nsga mentioned on GitHubpytorchSyntology: not harvested report
DataCanvasIO/Hypernets tfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MobileDets: Searching for Object Detection Architectures for Mobile Accelerators (arXiv:2004.14525; that paper's own run record: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
anonDEHB/DEHB Syntology: not harvested report
tensorflow/tpu tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It (arXiv:2403.14715; that paper's own run record: 9 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Evolutionary AlgorithmsImage ClassificationNeural Architecture SearchReinforcement Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet AmoebaNet-A GFLOPs 208 #382 of 1060 Archive leaderboard report
Image Classification ImageNet AmoebaNet-A Number of params 469M #382 of 1060 Archive leaderboard report
Image Classification ImageNet AmoebaNet-A Top 1 Accuracy 83.9% #382 of 1060 Archive leaderboard report
Neural Architecture Search CIFAR-10 Image Classification AmoebaNet-B + c/o Params 34.9M #8 of 19 Archive leaderboard report
Neural Architecture Search CIFAR-10 Image Classification AmoebaNet-B + c/o Percentage error 2.13 #8 of 19 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, ImageNet-16-120 REA Accuracy (Test) 45.54 #25 of 49 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, ImageNet-16-120 REA Search time (s) 12000 #25 of 49 Archive leaderboard report
Neural Architecture Search NATS-Bench Topology, CIFAR-10 RE (Real et al., 2019) Test Accuracy 94.13 #2 of 11 Archive leaderboard report
Neural Architecture Search NATS-Bench Topology, CIFAR-100 RE (Real et al., 2019) Test Accuracy 71.40 #4 of 11 Archive leaderboard report
Neural Architecture Search NATS-Bench Topology, ImageNet16-120 RE (Real et al., 2019) Test Accuracy 44.76 #5 of 11 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: Aging Evolution

Aging EvolutionAmoebaNetAverage PoolingConvolutionCosine AnnealingDropoutLabel SmoothingMax PoolingRMSPropSGD with MomentumScheduledDropPathSoftmaxSpatially Separable ConvolutionWeight Decay

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections