Papers › Low-shot Visual Recognition by Shrinking and Hallucinating Features

Low-shot Visual Recognition by Shrinking and Hallucinating Features

9 Jun 2016ICCV 2017 10arXiv:1606.02819archive 2025-07-28

Bharath Hariharan, Ross Girshick

Low-shot visual learning---the ability to recognize novel object categories from very few examples---is a hallmark of human visual intelligence. Existing machine learning approaches fail to generalize in the same way. To make progress on this foundational problem, we present a low-shot learning benchmark on complex images that mimics challenges faced by recognition systems in the wild. We then propose a) representation regularization techniques, and b) techniques to hallucinate additional training examples for data-starved classes. Together, our methods improve the effectiveness of convolutional networks in low-shot learning, improving the one-shot accuracy on novel classes by 2.3x on the challenging ImageNet dataset.

PaperPDFConference PDFCode

Syntology This paper's arXiv id is not in Syntology's Atlas id list (549,449 ids, as this build read them; the read time is in the build record), so this page links to no Syntology page for it. The list is not the whole graph; Syntology's feed shows papers as they enter the graph.

Code

facebookresearch/low-shot-shrink-hallucinate officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Matching Networks for One Shot Learning (arXiv:1606.04080; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
MyChocer/KGTN mentioned on GitHubpytorchSyntology: not harvested report
RajeevReddyIlavala/Low-Shot-Learning-Learning mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
sambi97/Low-shot-learning_-Deep-learning-project mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested 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

BIG-bench Machine LearningFew-Shot Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Image Classification ImageNet-FS (1-shot, novel) SGM (ResNet-50) Top-5 Accuracy (%) 52.9 #7 of 7 Archive leaderboard report
Few-Shot Image Classification ImageNet-FS (2-shot, novel) SGM (ResNet-50) Top-5 Accuracy (%) 67.0 #6 of 8 Archive leaderboard report
Few-Shot Image Classification ImageNet-FS (2-shot, novel) SGM w/G (ResNet-50) Top-5 Accuracy (%) 64.9 #8 of 8 Archive leaderboard report
Few-Shot Image Classification ImageNet-FS (5-shot, all) SGM (ResNet-50) Top-5 Accuracy (%) 77.4 #5 of 8 Archive leaderboard report
Few-Shot Image Classification ImageNet-FS (5-shot, all) SGM w/ G (ResNet-50) Top-5 Accuracy (%) 77.3 #7 of 8 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