Papers › Charting the Right Manifold: Manifold Mixup for Few-shot Learning

Charting the Right Manifold: Manifold Mixup for Few-shot Learning

28 Jul 2019arXiv:1907.12087archive 2025-07-28

Puneet Mangla, Mayank Singh, Abhishek Sinha, Nupur Kumari, Vineeth N. Balasubramanian, Balaji Krishnamurthy

Few-shot learning algorithms aim to learn model parameters capable of adapting to unseen classes with the help of only a few labeled examples. A recent regularization technique - Manifold Mixup focuses on learning a general-purpose representation, robust to small changes in the data distribution. Since the goal of few-shot learning is closely linked to robust representation learning, we study Manifold Mixup in this problem setting. Self-supervised learning is another technique that learns semantically meaningful features, using only the inherent structure of the data. This work investigates the role of learning relevant feature manifold for few-shot tasks using self-supervision and regularization techniques. We observe that regularizing the feature manifold, enriched via self-supervised techniques, with Manifold Mixup significantly improves few-shot learning performance. We show that our proposed method S2M2 beats the current state-of-the-art accuracy on standard few-shot learning datasets like CIFAR-FS, CUB, mini-ImageNet and tiered-ImageNet by 3-8 %. Through extensive experimentation, we show that the features learned using our approach generalize to complex few-shot evaluation tasks, cross-domain scenarios and are robust against slight changes to data distribution.

PaperPDFCode

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

Code

nupurkmr9/S2M2_fewshot officialmentioned in papermentioned on GitHubpytorchNOASSERTION report
DanielShalam/SOT mentioned on GitHubpytorch report
allenhaozhu/ease mentioned on GitHubpytorch report
breakaway7/p3dc-shot mentioned on GitHubpytorch report
danielshalam/bpa mentioned on GitHubpytorch report
yhu01/PT-MAP mentioned on GitHubpytorch 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.

Code Syntology ran Syntology

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

Tasks

Few-Shot Image ClassificationFew-Shot LearningRepresentation LearningSelf-Supervised Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Image Classification CIFAR-FS 5-way (1-shot) S2M2R Accuracy 74.81 #26 of 38 Archive leaderboard report
Few-Shot Image Classification CIFAR-FS 5-way (5-shot) S2M2R Accuracy 87.47 #23 of 39 Archive leaderboard report
Few-Shot Image Classification CUB 200 5-way 1-shot S2M2R Accuracy 80.68 #19 of 36 Archive leaderboard report
Few-Shot Image Classification CUB 200 5-way 5-shot S2M2R Accuracy 90.85 #18 of 32 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) S2M2R Accuracy 64.93 #59 of 105 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) S2M2R Accuracy 83.18 #37 of 95 Archive leaderboard report
Few-Shot Image Classification Tiered ImageNet 5-way (1-shot) S2M2R Accuracy 73.71 #23 of 49 Archive leaderboard report
Few-Shot Image Classification Tiered ImageNet 5-way (5-shot) S2M2R Accuracy 88.59 #13 of 51 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

Manifold MixupMixup

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