Papers › Laplacian Regularized Few-Shot Learning

Laplacian Regularized Few-Shot Learning

29 Jun 2020ICML 2020 1archive 2025-07-28

Imtiaz Masud Ziko; Jose Dolz; Eric Granger; Ismail Ben Ayed

We propose a transductive Laplacian-regularized inference for few-shot tasks. Given any feature embedding learned from the base classes, we minimize a quadratic binary-assignment function containing two terms: (1) a unary term assign- ing query samples to the nearest class prototype, and (2) a pairwise Laplacian term encouraging nearby query samples to have consistent label as- signments. Our transductive inference does not re-train the base model, and can be viewed as a graph clustering of the query set, subject to super- vision constraints from the support set. We derive a computationally efficient bound optimizer of a relaxation of our function, which computes inde- pendent (parallel) updates for each query sample, while guaranteeing convergence. Following a sim- ple cross-entropy training on the base classes, and without complex meta-learning strategies, we con- ducted comprehensive experiments over five few- shot learning benchmarks. Our LaplacianShot consistently outperforms state-of-the-art methods by significant margins across different models, settings, and data sets. Furthermore, our trans- ductive inference is very fast, with computational times that are close to inductive inference, and can be used for large-scale few-shot tasks.

PaperPDFConference PDFCode

Code

imtiazziko/LaplacianShot mentioned in paperpytorch 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

ClusteringFew-Shot Image ClassificationFew-Shot LearningGraph ClusteringMeta-Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Image Classification CUB 200 5-way 1-shot LaplacianShot Accuracy 80.96 #18 of 36 Archive leaderboard report
Few-Shot Image Classification CUB 200 5-way 5-shot LaplacianShot Accuracy 88.68 #22 of 32 Archive leaderboard report
Few-Shot Image Classification Mini-ImageNet-CUB 5-way (5-shot) LaplacianShot Accuracy 66.33 #5 of 8 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) LaplacianShot Accuracy 75.57 #23 of 105 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) LaplacianShot Accuracy 84.72 #25 of 95 Archive leaderboard report
Few-Shot Image Classification Tiered ImageNet 5-way (1-shot) LaplacianShot Accuracy 80.30 #11 of 49 Archive leaderboard report
Few-Shot Image Classification Tiered ImageNet 5-way (5-shot) LaplacianShot Accuracy 87.93 #16 of 51 Archive leaderboard report
Few-Shot Image Classification iNaturalist (227-way multi-shot) LaplacianShot Accuracy 74.97 #1 of 1 Archive leaderboard report
Few-Shot Image Classification miniImagenet → CUB (5-way 1-shot) LaplacianShot Accuracy 55.46 #1 of 1 Archive leaderboard report
Few-Shot Image Classification miniImagenet → CUB (5-way 5-shot) LaplacianShot Accuracy 66.33 #1 of 1 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

Transductive Inference

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