Papers › Circumventing Outliers of AutoAugment with Knowledge Distillation

Circumventing Outliers of AutoAugment with Knowledge Distillation

25 Mar 2020ECCV 2020 8arXiv:2003.11342archive 2025-07-28

Longhui Wei, An Xiao, Lingxi Xie, Xin Chen, Xiaopeng Zhang, Qi Tian

AutoAugment has been a powerful algorithm that improves the accuracy of many vision tasks, yet it is sensitive to the operator space as well as hyper-parameters, and an improper setting may degenerate network optimization. This paper delves deep into the working mechanism, and reveals that AutoAugment may remove part of discriminative information from the training image and so insisting on the ground-truth label is no longer the best option. To relieve the inaccuracy of supervision, we make use of knowledge distillation that refers to the output of a teacher model to guide network training. Experiments are performed in standard image classification benchmarks, and demonstrate the effectiveness of our approach in suppressing noise of data augmentation and stabilizing training. Upon the cooperation of knowledge distillation and AutoAugment, we claim the new state-of-the-art on ImageNet classification with a top-1 accuracy of 85.8%.

PaperPDFConference PDFCode

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

chenyang4/resmooth mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RandAugment: Practical automated data augmentation with a reduced search space (arXiv:1909.13719; that paper's own run record: 58 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 51 where Syntology's instrument failed) · 7 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

Data AugmentationGeneral ClassificationImage ClassificationKnowledge Distillationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet KDforAA (EfficientNet-B8) Number of params 88M #195 of 1060 Archive leaderboard report
Image Classification ImageNet KDforAA (EfficientNet-B8) Top 1 Accuracy 85.8% #195 of 1060 Archive leaderboard report
Image Classification ImageNet KDforAA (EfficientNet-B7) Number of params 66M #222 of 1060 Archive leaderboard report
Image Classification ImageNet KDforAA (EfficientNet-B7) Top 1 Accuracy 85.5% #222 of 1060 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

1x1 ConvolutionAutoAugmentAverage PoolingBatch NormalizationConvolutionDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionDropoutEfficientNetFixResInverted Residual BlockKnowledge DistillationLSTMPointwise ConvolutionRMSPropRandAugmentReLUShakeDropSigmoid ActivationSqueeze-and-Excitation BlockTanh ActivationWeight 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