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 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

kjunelee/MetaOptNet officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Understanding the Generalization of Bilevel Programming in Hyperparameter... (arXiv:2602.17947; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
cyvius96/few-shot-meta-baseline mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning (arXiv:2003.04390; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
goldblum/AdversarialQuerying mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Prototypical Networks for Few-shot Learning (arXiv:1703.05175; that paper's own run record: 50 ran (of which 14 constructed an object rather than computing a result; 29 with no instrument failure: 5 honoured, 0 violated, 24 with no contract checked; 21 where Syntology's instrument failed) · 14 unverified) and Adversarially Robust Few-Shot Learning: A Meta-Learning Approach (arXiv:1910.00982; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
nupurkmr9/S2M2_fewshot mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
xiangyu8/PT-MAP-sf mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Leveraging the Feature Distribution in Transfer-based Few-Shot Learning (arXiv:2006.03806; that paper's own run record: 22 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 9 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
yinboc/few-shot-meta-baseline mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A Closer Look at Few-shot Classification (arXiv:1904.04232; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
learnables/learn2learn pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks (arXiv:1703.03400; that paper's own run record: 103 ran (of which 35 constructed an object rather than computing a result; 72 with no instrument failure: 6 honoured, 1 violated, 65 with no contract checked; 31 where Syntology's instrument failed) · 51 unverified), Prototypical Networks for Few-shot Learning (arXiv:1703.05175; that paper's own run record: 50 ran (of which 14 constructed an object rather than computing a result; 29 with no instrument failure: 5 honoured, 0 violated, 24 with no contract checked; 21 where Syntology's instrument failed) · 14 unverified), On First-Order Meta-Learning Algorithms (arXiv:1803.02999; that paper's own run record: 27 ran (of which 2 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 2 violated, 6 with no contract checked; 18 where Syntology's instrument failed) · 15 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

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