</> Code with Papers by Syntology

Papers › Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks

Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks

13 Dec 2020arXiv:2012.07176archive 2025-07-28

Reza Esfandiarpoor, Amy Pu, Mohsen Hajabdollahi, Stephen H. Bach

In many practical few-shot learning problems, even though labeled examples are scarce, there are abundant auxiliary datasets that potentially contain useful information. We propose the problem of extended few-shot learning to study these scenarios. We then introduce a framework to address the challenges of efficiently selecting and effectively using auxiliary data in few-shot image classification. Given a large auxiliary dataset and a notion of semantic similarity among classes, we automatically select pseudo shots, which are labeled examples from other classes related to the target task. We show that naive approaches, such as (1) modeling these additional examples the same as the target task examples or (2) using them to learn features via transfer learning, only increase accuracy by a modest amount. Instead, we propose a masking module that adjusts the features of auxiliary data to be more similar to those of the target classes. We show that this masking module performs better than naively modeling the support examples and transfer learning by 4.68 and 6.03 percentage points, respectively.

PaperPDFCode

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

Code

BatsResearch/efsl officialmentioned in papermentioned on GitHubpytorch report
Reza-esfandiarpoor/pseudo-shots 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

Few-Shot Image ClassificationFew-Shot LearningImage ClassificationSemantic SimilaritySemantic Textual SimilarityTransfer Learningimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Image Classification CIFAR-FS - 1-Shot Learning pseudo-shots Accuracy 81.87% #1 of 1 Archive leaderboard report
Few-Shot Image Classification CIFAR-FS - 5-Shot Learning pseudo-shots Accuracy 89.12 #1 of 1 Archive leaderboard report
Few-Shot Image Classification CIFAR-FS 5-way (1-shot) pseudo-shots Accuracy 81.87 #12 of 38 Archive leaderboard report
Few-Shot Image Classification CIFAR-FS 5-way (5-shot) pseudo-shots Accuracy 89.12 #15 of 39 Archive leaderboard report
Few-Shot Image Classification FC100 5-way (1-shot) pseudo-shots Accuracy 50.57 #5 of 22 Archive leaderboard report
Few-Shot Image Classification FC100 5-way (5-shot) pseudo-shots Accuracy 61.58 #15 of 22 Archive leaderboard report
Few-Shot Image Classification Fewshot-CIFAR100 - 1-Shot Learning pseudo-shots Accuracy 50.57% #1 of 1 Archive leaderboard report
Few-Shot Image Classification Fewshot-CIFAR100 - 5-Shot Learning pseudo-shots Accuracy 61.58% #1 of 1 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) pseudo-shots Accuracy 73.35 #26 of 105 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) pseudo-shots Accuracy 82.51 #40 of 95 Archive leaderboard report
Few-Shot Image Classification Tiered ImageNet 5-way (1-shot) pseudo-shots Accuracy 76.55 #17 of 49 Archive leaderboard report
Few-Shot Image Classification Tiered ImageNet 5-way (5-shot) pseudo-shots Accuracy 86.82 #22 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