Papers › Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions

Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions

10 Dec 2018CVPR 2020 6arXiv:1812.03664archive 2025-07-28

Han-Jia Ye, Hexiang Hu, De-Chuan Zhan, Fei Sha

Learning with limited data is a key challenge for visual recognition. Many few-shot learning methods address this challenge by learning an instance embedding function from seen classes and apply the function to instances from unseen classes with limited labels. This style of transfer learning is task-agnostic: the embedding function is not learned optimally discriminative with respect to the unseen classes, where discerning among them leads to the target task. In this paper, we propose a novel approach to adapt the instance embeddings to the target classification task with a set-to-set function, yielding embeddings that are task-specific and are discriminative. We empirically investigated various instantiations of such set-to-set functions and observed the Transformer is most effective -- as it naturally satisfies key properties of our desired model. We denote this model as FEAT (few-shot embedding adaptation w/ Transformer) and validate it on both the standard few-shot classification benchmark and four extended few-shot learning settings with essential use cases, i.e., cross-domain, transductive, generalized few-shot learning, and low-shot learning. It archived consistent improvements over baseline models as well as previous methods and established the new state-of-the-art results on two benchmarks.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Sha-Lab/FEAT officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Prototypical Networks for Few-shot Learning (arXiv:1703.05175; that paper's own run record: 50 ran (of which 14 constructed an object rather than computing a result; 29 with no instrument failure: 5 honoured, 0 violated, 24 with no contract checked; 21 where Syntology's instrument failed) · 14 unverified); nothing checks that they implement this paper's method. report
Alibaba-AAIG/SSL-FEW-SHOT mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning Representations by Maximizing Mutual Information Across Views (arXiv:1906.00910; that paper's own run record: 8 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
DanielShalam/SOT mentioned on GitHubpytorchSyntology: not harvested report
danielshalam/bpa mentioned on GitHubpytorchSyntology: not harvested report
han-jia/lastshot mentioned on GitHubpytorchSyntology: not harvested report
sicara/easy-few-shot-learning pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Prototypical Networks for Few-shot Learning (arXiv:1703.05175; that paper's own run record: 50 ran (of which 14 constructed an object rather than computing a result; 29 with no instrument failure: 5 honoured, 0 violated, 24 with no contract checked; 21 where Syntology's instrument failed) · 14 unverified), Laplacian Regularized Few-Shot Learning (arXiv:2006.15486; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified) and Transductive Information Maximization For Few-Shot Learning (arXiv:2008.11297; that paper's own run record: 9 ran (of which 2 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. 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

Few-Shot Image ClassificationFew-Shot LearningGeneral ClassificationGeneralized Few-Shot LearningTransfer Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Image Classification CUB 200 5-way 1-shot feat (ProtoNet) Accuracy 68.65 #30 of 36 Archive leaderboard report
Few-Shot Image Classification CUB 200 5-way 5-shot feat (ProtoNet) Accuracy 83.03 #28 of 32 Archive leaderboard report
Few-Shot Image Classification Mini-ImageNet-CUB 5-way (1-shot) FEAT (Ye et al., 2018) Accuracy 39.00 #11 of 12 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) feat+ (ProtoNet-ResNet) Accuracy 61.72 #70 of 105 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) feat+ (ProtoNet-ResNet) Accuracy 78.38 #59 of 95 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

1x1 ConvolutionAbsolute Position EncodingsAdamAttentionAverage PoolingBPEBatch NormalizationBottleneck Residual BlockConvolutionDense ConnectionsDropoutGlobal Average PoolingKaiming InitializationLabel SmoothingLayer NormalizationLinear LayerMax PoolingMulti-Head AttentionPosition-Wise Feed-Forward LayerReLUResidual BlockResidual ConnectionSoftmaxTransformer

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