Papers › Meta-Learning with Differentiable Convex Optimization

Meta-Learning with Differentiable Convex Optimization

7 Apr 2019CVPR 2019 6arXiv:1904.03758archive 2025-07-28

Kwonjoon Lee, Subhransu Maji, Avinash Ravichandran, Stefano Soatto

Many meta-learning approaches for few-shot learning rely on simple base learners such as nearest-neighbor classifiers. However, even in the few-shot regime, discriminatively trained linear predictors can offer better generalization. We propose to use these predictors as base learners to learn representations for few-shot learning and show they offer better tradeoffs between feature size and performance across a range of few-shot recognition benchmarks. Our objective is to learn feature embeddings that generalize well under a linear classification rule for novel categories. To efficiently solve the objective, we exploit two properties of linear classifiers: implicit differentiation of the optimality conditions of the convex problem and the dual formulation of the optimization problem. This allows us to use high-dimensional embeddings with improved generalization at a modest increase in computational overhead. Our approach, named MetaOptNet, achieves state-of-the-art performance on miniImageNet, tieredImageNet, CIFAR-FS, and FC100 few-shot learning benchmarks. Our code is available at https://github.com/kjunelee/MetaOptNet.

PaperPDFConference PDFCode

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

Code

kjunelee/MetaOptNet officialmentioned in papermentioned on GitHubpytorch report
cyvius96/few-shot-meta-baseline mentioned on GitHubpytorchMIT report
goldblum/AdversarialQuerying mentioned on GitHubpytorch report
nupurkmr9/S2M2_fewshot mentioned on GitHubpytorchNOASSERTION report
xiangyu8/PT-MAP-sf mentioned on GitHubpytorch report
yinboc/few-shot-meta-baseline 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 LearningMeta-Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Image Classification CIFAR-FS 5-way (1-shot) MetaOptNet-SVM-trainval Accuracy 72.8 #32 of 38 Archive leaderboard report
Few-Shot Image Classification CIFAR-FS 5-way (5-shot) MetaOptNet-SVM-trainval Accuracy 85 #32 of 39 Archive leaderboard report
Few-Shot Image Classification FC100 5-way (1-shot) MetaOptNet-SVM-trainval Accuracy 47.2 #12 of 22 Archive leaderboard report
Few-Shot Image Classification FC100 5-way (5-shot) MetaOptNet-SVM-trainval Accuracy 62.5 #14 of 22 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) MetaOptNet-SVM-trainval Accuracy 64.09 #63 of 105 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) MetaOptNet-SVM-trainval Accuracy 80 #54 of 95 Archive leaderboard report
Few-Shot Image Classification Tiered ImageNet 5-way (1-shot) MetaOptNet-SVM-trainval Accuracy 65.81 #43 of 49 Archive leaderboard report
Few-Shot Image Classification Tiered ImageNet 5-way (5-shot) MetaOptNet-SVM-trainval Accuracy 81.75 #42 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.

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