{"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/adaptive-fine-grained-sketch-based-image","title":"Adaptive Fine-Grained Sketch-Based Image Retrieval","arxiv_id":"2207.01723","date":"2022-07-04","proceeding":null,"authors":["Ayan Kumar Bhunia","Aneeshan Sain","Parth Shah","Animesh Gupta","Pinaki Nath Chowdhury","Tao Xiang","Yi-Zhe Song"],"abstract":"The recent focus on Fine-Grained Sketch-Based Image Retrieval (FG-SBIR) has shifted towards generalising a model to new categories without any training data from them. In real-world applications, however, a trained FG-SBIR model is often applied to both new categories and different human sketchers, i.e., different drawing styles. Although this complicates the generalisation problem, fortunately, a handful of examples are typically available, enabling the model to adapt to the new category/style. In this paper, we offer a novel perspective -- instead of asking for a model that generalises, we advocate for one that quickly adapts, with just very few samples during testing (in a few-shot manner). To solve this new problem, we introduce a novel model-agnostic meta-learning (MAML) based framework with several key modifications: (1) As a retrieval task with a margin-based contrastive loss, we simplify the MAML training in the inner loop to make it more stable and tractable. (2) The margin in our contrastive loss is also meta-learned with the rest of the model. (3) Three additional regularisation losses are introduced in the outer loop, to make the meta-learned FG-SBIR model more effective for category/style adaptation. Extensive experiments on public datasets suggest a large gain over generalisation and zero-shot based approaches, and a few strong few-shot baselines.","url_abs":"https://arxiv.org/abs/2207.01723v3","url_pdf":"https://arxiv.org/pdf/2207.01723v3.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":"adaptive-fine-grained-sketch-based-image","repo_url":"https://github.com/ayankumarbhunia/adaptive-fgsbir","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"sketch-based-image-retrieval","task_name":"Sketch-Based Image Retrieval"}],"methods":[{"method_slug":"maml","method_name":"MAML"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2207.01723","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}