{"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/pseudo-shots-few-shot-learning-with-auxiliary","title":"Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks","arxiv_id":"2012.07176","date":"2020-12-13","proceeding":null,"authors":["Reza Esfandiarpoor","Amy Pu","Mohsen Hajabdollahi","Stephen H. Bach"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2012.07176v3","url_pdf":"https://arxiv.org/pdf/2012.07176v3.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":"pseudo-shots-few-shot-learning-with-auxiliary","repo_url":"https://github.com/BatsResearch/efsl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"pseudo-shots-few-shot-learning-with-auxiliary","repo_url":"https://github.com/Reza-esfandiarpoor/pseudo-shots","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"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":"image-classification","task_name":"Image Classification"},{"task_slug":"semantic-similarity","task_name":"Semantic Similarity"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-image-classification-on-cifar-fs-1","task":"Few-Shot Image Classification","dataset":"CIFAR-FS - 1-Shot Learning","model":"pseudo-shots","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"81.87%"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-cifar-fs-5-2","task":"Few-Shot Image Classification","dataset":"CIFAR-FS - 5-Shot Learning","model":"pseudo-shots","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"89.12"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-cifar-fs-5","task":"Few-Shot Image Classification","dataset":"CIFAR-FS 5-way (1-shot)","model":"pseudo-shots","rank_in_archive_order":12,"of":38,"metrics":{"Accuracy":"81.87"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-cifar-fs-5-1","task":"Few-Shot Image Classification","dataset":"CIFAR-FS 5-way (5-shot)","model":"pseudo-shots","rank_in_archive_order":15,"of":39,"metrics":{"Accuracy":"89.12"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-fc100-5-way","task":"Few-Shot Image Classification","dataset":"FC100 5-way (1-shot)","model":"pseudo-shots","rank_in_archive_order":5,"of":22,"metrics":{"Accuracy":"50.57"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-fc100-5-way-1","task":"Few-Shot Image Classification","dataset":"FC100 5-way (5-shot)","model":"pseudo-shots","rank_in_archive_order":15,"of":22,"metrics":{"Accuracy":"61.58"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-fewshot","task":"Few-Shot Image Classification","dataset":"Fewshot-CIFAR100 - 1-Shot Learning","model":"pseudo-shots","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"50.57%"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-fewshot-1","task":"Few-Shot Image Classification","dataset":"Fewshot-CIFAR100 - 5-Shot Learning","model":"pseudo-shots","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"61.58%"},"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":"pseudo-shots","rank_in_archive_order":26,"of":105,"metrics":{"Accuracy":"73.35"},"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":"pseudo-shots","rank_in_archive_order":40,"of":95,"metrics":{"Accuracy":"82.51"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-tiered","task":"Few-Shot Image Classification","dataset":"Tiered ImageNet 5-way (1-shot)","model":"pseudo-shots","rank_in_archive_order":17,"of":49,"metrics":{"Accuracy":"76.55"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-tiered-1","task":"Few-Shot Image Classification","dataset":"Tiered ImageNet 5-way (5-shot)","model":"pseudo-shots","rank_in_archive_order":22,"of":51,"metrics":{"Accuracy":"86.82"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2012.07176","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}