Papers › TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning

TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning

16 May 2019arXiv:1905.06549archive 2025-07-28

Sung Whan Yoon, Jun Seo, Jaekyun Moon

Handling previously unseen tasks after given only a few training examples continues to be a tough challenge in machine learning. We propose TapNets, neural networks augmented with task-adaptive projection for improved few-shot learning. Here, employing a meta-learning strategy with episode-based training, a network and a set of per-class reference vectors are learned across widely varying tasks. At the same time, for every episode, features in the embedding space are linearly projected into a new space as a form of quick task-specific conditioning. The training loss is obtained based on a distance metric between the query and the reference vectors in the projection space. Excellent generalization results in this way. When tested on the Omniglot, miniImageNet and tieredImageNet datasets, we obtain state of the art classification accuracies under various few-shot scenarios.

PaperPDFCode

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

Code

istarjun/TapNet officialmentioned in paper 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 LearningMeta-Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) TapNet Accuracy 61.65 #71 of 105 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) TapNet Accuracy 76.36 #67 of 95 Archive leaderboard report
Few-Shot Image Classification OMNIGLOT - 1-Shot, 20-way TapNet Accuracy 98.07% #4 of 20 Archive leaderboard report
Few-Shot Image Classification OMNIGLOT - 5-Shot, 20-way TapNet Accuracy 99.49% #4 of 19 Archive leaderboard report
Few-Shot Image Classification Tiered ImageNet 5-way (1-shot) TapNet Accuracy 63.08 #44 of 49 Archive leaderboard report
Few-Shot Image Classification Tiered ImageNet 5-way (5-shot) TapNet Accuracy 80.26 #43 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