Papers › Instance Credibility Inference for Few-Shot Learning

Instance Credibility Inference for Few-Shot Learning

26 Mar 2020CVPR 2020 6arXiv:2003.11853archive 2025-07-28

Yikai Wang, Chengming Xu, Chen Liu, Li Zhang, Yanwei Fu

Few-shot learning (FSL) aims to recognize new objects with extremely limited training data for each category. Previous efforts are made by either leveraging meta-learning paradigm or novel principles in data augmentation to alleviate this extremely data-scarce problem. In contrast, this paper presents a simple statistical approach, dubbed Instance Credibility Inference (ICI) to exploit the distribution support of unlabeled instances for few-shot learning. Specifically, we first train a linear classifier with the labeled few-shot examples and use it to infer the pseudo-labels for the unlabeled data. To measure the credibility of each pseudo-labeled instance, we then propose to solve another linear regression hypothesis by increasing the sparsity of the incidental parameters and rank the pseudo-labeled instances with their sparsity degree. We select the most trustworthy pseudo-labeled instances alongside the labeled examples to re-train the linear classifier. This process is iterated until all the unlabeled samples are included in the expanded training set, i.e. the pseudo-label is converged for unlabeled data pool. Extensive experiments under two few-shot settings show that our simple approach can establish new state-of-the-arts on four widely used few-shot learning benchmark datasets including miniImageNet, tieredImageNet, CIFAR-FS, and CUB. Our code is available at: https://github.com/Yikai-Wang/ICI-FSL

PaperPDFConference PDFCode

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

Code

Yikai-Wang/ICI-FSL officialmentioned in papermentioned 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

Data AugmentationFew-Shot Image ClassificationFew-Shot LearningMeta-LearningPseudo Label

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Image Classification CIFAR-FS 5-way (1-shot) ICI Accuracy 76.51 #21 of 38 Archive leaderboard report
Few-Shot Image Classification CIFAR-FS 5-way (5-shot) ICI Accuracy 84.32 #33 of 39 Archive leaderboard report
Few-Shot Image Classification CUB 200 5-way 1-shot ICI Accuracy 89.58 #12 of 36 Archive leaderboard report
Few-Shot Image Classification CUB 200 5-way 5-shot ICI Accuracy 92.48 #12 of 32 Archive leaderboard report
Few-Shot Image Classification Dirichlet Mini-Imagenet (5-way, 1-shot) LR-ICI 1:1 Accuracy 58.7 #8 of 12 Archive leaderboard report
Few-Shot Image Classification Dirichlet Mini-Imagenet (5-way, 5-shot) LR-ICI 1:1 Accuracy 73.5 #9 of 12 Archive leaderboard report
Few-Shot Image Classification Dirichlet Tiered-Imagenet (5-way, 1-shot) LR+ICI 1:1 Accuracy 74.6 #2 of 9 Archive leaderboard report
Few-Shot Image Classification Dirichlet Tiered-Imagenet (5-way, 5-shot) LR+ICI 1:1 Accuracy 85.1 #4 of 9 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) ICI Accuracy 69.66 #36 of 105 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) ICI Accuracy 80.11 #53 of 95 Archive leaderboard report
Few-Shot Image Classification Tiered ImageNet 5-way (1-shot) ICI Accuracy 84.01 #7 of 49 Archive leaderboard report
Few-Shot Image Classification Tiered ImageNet 5-way (5-shot) ICI Accuracy 89.00 #12 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

Linear Regression

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