{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T03:05:51Z","timestamp":1773803151310,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"28","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Large models such as Vision Transformers (ViTs) have demonstrated remarkable superiority over smaller architectures like ResNet in few-shot classification, owing to their powerful representational capacity. However, fine-tuning such large models demands extensive GPU memory and prolonged training time, making them impractical for many real-world low-resource scenarios. To bridge this gap, we propose EfficientFSL, a query-only fine-tuning framework tailored specifically for few-shot classification with ViT, which achieves competitive performance while significantly reducing computational overhead. EfficientFSL fully leverages the knowledge embedded in the pre-trained model and its strong comprehension ability, achieving high classification accuracy with an extremely small number of tunable parameters. Specifically, we introduce a lightweight trainable Forward Block to synthesize task-specific queries that extract informative features from the intermediate representations of the pre-trained model in a query-only manner. We further propose a Combine Block to fuse multi-layer outputs, enhancing the depth and robustness of feature representations. Finally, a Support-Query Attention Block mitigates distribution shift by adjusting prototypes to align with the query set distribution.  With minimal trainable parameters, EfficientFSL achieves state-of-the-art performance on four in-domain few-shot datasets and six cross-domain datasets, demonstrating its effectiveness in real-world applications.<\/jats:p>","DOI":"10.1609\/aaai.v40i28.39519","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T01:40:53Z","timestamp":1773798053000},"page":"23478-23486","source":"Crossref","is-referenced-by-count":0,"title":["EfficientFSL: Enhancing Few-Shot Classification via Query-Only Tuning In Vision Transformers"],"prefix":"10.1609","volume":"40","author":[{"given":"Wenwen","family":"Liao","sequence":"first","affiliation":[]},{"given":"Hang","family":"Ruan","sequence":"additional","affiliation":[]},{"given":"Jianbo","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Bing","family":"Song","sequence":"additional","affiliation":[]},{"given":"Yuansong","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Xiaofeng","family":"Yang","sequence":"additional","affiliation":[]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/39519\/43480","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/39519\/43480","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T01:40:54Z","timestamp":1773798054000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/39519"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"28","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i28.39519","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}