{"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/more-photos-are-all-you-need-semi-supervised","title":"More Photos are All You Need: Semi-Supervised Learning for Fine-Grained Sketch Based Image Retrieval","arxiv_id":"2103.13990","date":"2021-03-25","proceeding":"CVPR 2021 1","authors":["Ayan Kumar Bhunia","Pinaki Nath Chowdhury","Aneeshan Sain","Yongxin Yang","Tao Xiang","Yi-Zhe Song"],"abstract":"A fundamental challenge faced by existing Fine-Grained Sketch-Based Image Retrieval (FG-SBIR) models is the data scarcity -- model performances are largely bottlenecked by the lack of sketch-photo pairs. Whilst the number of photos can be easily scaled, each corresponding sketch still needs to be individually produced. In this paper, we aim to mitigate such an upper-bound on sketch data, and study whether unlabelled photos alone (of which they are many) can be cultivated for performances gain. In particular, we introduce a novel semi-supervised framework for cross-modal retrieval that can additionally leverage large-scale unlabelled photos to account for data scarcity. At the centre of our semi-supervision design is a sequential photo-to-sketch generation model that aims to generate paired sketches for unlabelled photos. Importantly, we further introduce a discriminator guided mechanism to guide against unfaithful generation, together with a distillation loss based regularizer to provide tolerance against noisy training samples. Last but not least, we treat generation and retrieval as two conjugate problems, where a joint learning procedure is devised for each module to mutually benefit from each other. Extensive experiments show that our semi-supervised model yields significant performance boost over the state-of-the-art supervised alternatives, as well as existing methods that can exploit unlabelled photos for FG-SBIR.","url_abs":"https://arxiv.org/abs/2103.13990v1","url_pdf":"https://arxiv.org/pdf/2103.13990v1.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":"more-photos-are-all-you-need-semi-supervised","repo_url":"https://github.com/AyanKumarBhunia/semisupervised-FGSBIR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"cross-modal-retrieval","task_name":"Cross-Modal Retrieval"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"semi-supervised-sketch-based-image-retrieval","task_name":"Semi-Supervised Sketch Based Image Retrieval"},{"task_slug":"sketch-based-image-retrieval","task_name":"Sketch-Based Image Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2103.13990","atlas_url":"https://app.syntology.ai/?focus=2103.13990","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}