eprintid: 10198885 rev_number: 7 eprint_status: archive userid: 699 dir: disk0/10/19/88/85 datestamp: 2024-10-25 09:33:01 lastmod: 2024-10-25 09:33:01 status_changed: 2024-10-25 09:33:01 type: article metadata_visibility: show sword_depositor: 699 creators_name: Zhang, Zhimin creators_name: Chang, Dongliang creators_name: Zhu, Rui creators_name: Li, Xiaoxu creators_name: Ma, Zhanyu creators_name: Xue, Jing-Hao title: Query-aware Cross-mixup and Cross-reconstruction for Few-shot Fine-grained Image Classification ispublished: inpress divisions: UCL divisions: B04 divisions: C06 divisions: F61 note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and conditions. abstract: Few-shot fine-grained image classification is prominent but challenging in computer vision, aiming to distinguish sub-classes under the same parent class but with only a few labeled support samples. Data augmentation techniques were explored to address the few-shot issue, but they often fail to mitigate the bias between support and query samples. Therefore, in this paper we propose a query-aware cross-mixup and cross-reconstruction method to address both few-shot and fine-grained issues. Specifically, in the training phase, we randomly select query samples and mix them with the support samples from the same class to augment the support set. This first strategy ensures the augmented support set query-aware within each sub-class. Then, we reconstruct both query samples and support samples from both original and cross-mixed support samples, thus leveraging both cross-reconstruction and self-reconstruction to enhance classification. This second strategy, enabling the reconstruction also query-aware, further mitigates the bias between support and query samples, leading to more reliable generalization. We evaluate our proposed method on four widely used few-shot fine-grained image classification datasets, and experimental results demonstrate its effectiveness in achieving the state-of-the-art classification performance. date: 2024-10-22 date_type: published publisher: Institute of Electrical and Electronics Engineers (IEEE) official_url: http://dx.doi.org/10.1109/tcsvt.2024.3484530 oa_status: green full_text_type: other language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 2329522 doi: 10.1109/tcsvt.2024.3484530 lyricists_name: Xue, Jinghao lyricists_id: JXUEX60 actors_name: Flynn, Bernadette actors_id: BFFLY94 actors_role: owner full_text_status: public publication: IEEE Transactions on Circuits and Systems for Video Technology pagerange: 1-12 citation: Zhang, Zhimin; Chang, Dongliang; Zhu, Rui; Li, Xiaoxu; Ma, Zhanyu; Xue, Jing-Hao; (2024) Query-aware Cross-mixup and Cross-reconstruction for Few-shot Fine-grained Image Classification. IEEE Transactions on Circuits and Systems for Video Technology pp. 1-12. 10.1109/tcsvt.2024.3484530 <https://doi.org/10.1109/tcsvt.2024.3484530>. (In press). Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10198885/1/Query-aware_Cross-mixup_and_Cross-reconstruction_for_Few-shot_Fine-grained_Image_Classification.pdf