{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/learning-embedding-adaptation-for-few-shot","title":"Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions","arxiv_id":"1812.03664","date":"2018-12-10","proceeding":"CVPR 2020 6","authors":["Han-Jia Ye","Hexiang Hu","De-Chuan Zhan","Fei Sha"],"abstract":"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.","url_abs":"https://arxiv.org/abs/1812.03664v6","url_pdf":"https://arxiv.org/pdf/1812.03664v6.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"learning-embedding-adaptation-for-few-shot","repo_url":"https://github.com/Sha-Lab/FEAT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-embedding-adaptation-for-few-shot","repo_url":"https://github.com/Alibaba-AAIG/SSL-FEW-SHOT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-embedding-adaptation-for-few-shot","repo_url":"https://github.com/DanielShalam/SOT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"learning-embedding-adaptation-for-few-shot","repo_url":"https://github.com/danielshalam/bpa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"learning-embedding-adaptation-for-few-shot","repo_url":"https://github.com/han-jia/lastshot","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"learning-embedding-adaptation-for-few-shot","repo_url":"https://github.com/sicara/easy-few-shot-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"few-shot-image-classification","task_name":"Few-Shot Image Classification"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"generalized-few-shot-learning","task_name":"Generalized Few-Shot Learning"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-image-classification-on-cub-200-5-1","task":"Few-Shot Image Classification","dataset":"CUB 200 5-way 1-shot","model":"feat (ProtoNet)","rank_in_archive_order":30,"of":36,"metrics":{"Accuracy":"68.65"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-cub-200-5","task":"Few-Shot Image Classification","dataset":"CUB 200 5-way 5-shot","model":"feat (ProtoNet)","rank_in_archive_order":28,"of":32,"metrics":{"Accuracy":"83.03"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-mini-5","task":"Few-Shot Image Classification","dataset":"Mini-ImageNet-CUB 5-way (1-shot)","model":"FEAT (Ye et al., 2018)","rank_in_archive_order":11,"of":12,"metrics":{"Accuracy":"39.00"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-mini-2","task":"Few-Shot Image Classification","dataset":"Mini-Imagenet 5-way (1-shot)","model":"feat+ (ProtoNet-ResNet)","rank_in_archive_order":70,"of":105,"metrics":{"Accuracy":"61.72"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-mini-3","task":"Few-Shot Image Classification","dataset":"Mini-Imagenet 5-way (5-shot)","model":"feat+ (ProtoNet-ResNet)","rank_in_archive_order":59,"of":95,"metrics":{"Accuracy":"78.38"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1812.03664","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}