Papers › Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup

Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup

30 Nov 2021arXiv:2111.15454archive 2025-07-28

Siyuan Li, Zicheng Liu, Zedong Wang, Di wu, Zihan Liu, Stan Z. Li

Mixup is a well-known data-dependent augmentation technique for DNNs, consisting of two sub-tasks: mixup generation and classification. However, the recent dominant online training method confines mixup to supervised learning (SL), and the objective of the generation sub-task is limited to selected sample pairs instead of the whole data manifold, which might cause trivial solutions. To overcome such limitations, we comprehensively study the objective of mixup generation and propose Scenario-Agnostic Mixup (SAMix) for both SL and Self-supervised Learning (SSL) scenarios. Specifically, we hypothesize and verify the objective function of mixup generation as optimizing local smoothness between two mixed classes subject to global discrimination from other classes. Accordingly, we propose η-balanced mixup loss for complementary learning of the two sub-objectives. Meanwhile, a label-free generation sub-network is designed, which effectively provides non-trivial mixup samples and improves transferable abilities. Moreover, to reduce the computational cost of online training, we further introduce a pre-trained version, SAMix^𝒫, achieving more favorable efficiency and generalizability. Extensive experiments on nine SL and SSL benchmarks demonstrate the consistent superiority and versatility of SAMix compared with existing methods.

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

Westlake-AI/openmixup officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to mixup: Beyond Empirical Risk Minimization (arXiv:1710.09412; that paper's own run record: 36 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 22 where Syntology's instrument failed) · 11 unverified), Visualizing the Loss Landscape of Neural Nets (arXiv:1712.09913; that paper's own run record: 3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified), CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features (arXiv:1905.04899; that paper's own run record: 17 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified) and 1 more (every one in this page's JSON twin); 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 AugmentationImage ClassificationRepresentation LearningSelf-Supervised Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification CIFAR-100 WRN-28-8 +SAMix Percentage correct 85.50 #61 of 211 Archive leaderboard report
Image Classification CIFAR-100 ResNeXt-50(32x4d) + SAMix Percentage correct 84.42 #76 of 211 Archive leaderboard report
Image Classification ImageNet ResNet-101 (SAMix) Number of params 44.6M #668 of 1060 Archive leaderboard report
Image Classification ImageNet ResNet-101 (SAMix) Top 1 Accuracy 81.08% #668 of 1060 Archive leaderboard report
Image Classification ImageNet ResNet-50 (SAMix) Number of params 25.6M #753 of 1060 Archive leaderboard report
Image Classification ImageNet ResNet-50 (SAMix) Top 1 Accuracy 79.41% #753 of 1060 Archive leaderboard report
Image Classification ImageNet ResNet-34 (SAMix) Number of params 21.8M #915 of 1060 Archive leaderboard report
Image Classification ImageNet ResNet-34 (SAMix) Top 1 Accuracy 76.35% #915 of 1060 Archive leaderboard report
Image Classification ImageNet ResNet-18 (SAMix) Number of params 11.7M #999 of 1060 Archive leaderboard report
Image Classification ImageNet ResNet-18 (SAMix) Top 1 Accuracy 72.33% #999 of 1060 Archive leaderboard report
Image Classification Places205 SAMix (ResNet-50 Supervised) Top 1 Accuracy 64.3 #7 of 15 Archive leaderboard report
Image Classification Tiny ImageNet Classification ResNeXt-50 (SAMix) Validation Acc 72.18% #13 of 23 Archive leaderboard report
Image Classification Tiny ImageNet Classification ResNet18 (SAMix) Validation Acc 68.89% #17 of 23 Archive leaderboard report
Image Classification iNaturalist 2018 ResNeXt-101 (SAMix) Top-1 Accuracy 70.54% #36 of 60 Archive leaderboard report
Image Classification iNaturalist 2018 ResNet-50 (SAMix) Top-1 Accuracy 64.84% #48 of 60 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

AttentionInfoNCELinear LayerMixupMoCoMulti-Head AttentionResidual ConnectionSoftmaxVision Transformer

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