{"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/unsupervised-few-shot-image-classification-by","title":"Unsupervised Few-Shot Image Classification by Learning Features into Clustering Space","arxiv_id":null,"date":"2022-10-21","proceeding":"European Conference on Computer Vision 2022 10","authors":["Shuo Li","Fang Liu","Zehua Hao","Kaibo Zhao","Licheng Jia"],"abstract":"Most few-shot image classification methods are trained based on tasks. Usually, tasks are built on base classes with a large number of labeled images, which consumes large effort. Unsupervised few-shot image classification methods do not need labeled images, because they require tasks to be built on unlabeled images. In order to efficiently build tasks with unlabeled images, we propose a novel single-stage clustering method: Learning Features into Clustering Space (LF2CS), which first set a separable clustering space by fixing the clustering centers and then use a learnable model to learn features into the clustering space. Based on our LF2CS, we put forward an image sampling and c-way k-shot task building method. With this, we propose a novel unsupervised few-shot image classification method, which jointly learns the learnable model, clustering and few-shot image classification. Experiments and visualization show that our LF2CS has a strong ability to generalize to the novel categories. From the perspective of image sampling, we implement four baselines according to how to build tasks. We conduct experiments on the Omniglot, miniImageNet, tieredImageNet and CIFARFS datasets based on the Conv-4 and ResNet-12 backbones. Experimental results show that\r\nours outperform the state-of-the-art methods.","url_abs":"https://www.ecva.net/papers/eccv_2022/papers_ECCV/html/7167_ECCV_2022_paper.php","url_pdf":"https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136910406.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":"unsupervised-few-shot-image-classification-by","repo_url":"https://github.com/xidianai/LF2CS","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MPL-2.0"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"few-shot-image-classification","task_name":"Few-Shot Image Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"unsupervised-few-shot-image-classification","task_name":"Unsupervised Few-Shot Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-few-shot-image-classification-on","task":"Unsupervised Few-Shot Image Classification","dataset":"Mini-Imagenet 5-way (1-shot)","model":"LF2CS","rank_in_archive_order":12,"of":28,"metrics":{"Accuracy":"53.14"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-few-shot-image-classification-on-1","task":"Unsupervised Few-Shot Image Classification","dataset":"Mini-Imagenet 5-way (5-shot)","model":"LF2CS","rank_in_archive_order":13,"of":28,"metrics":{"Accuracy":"67.36"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-few-shot-image-classification-on-2","task":"Unsupervised Few-Shot Image Classification","dataset":"Tiered ImageNet 5-way (1-shot)","model":"LF2CS","rank_in_archive_order":6,"of":12,"metrics":{"Accuracy":"53.16"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-few-shot-image-classification-on-3","task":"Unsupervised Few-Shot Image Classification","dataset":"Tiered ImageNet 5-way (5-shot)","model":"LF2CS","rank_in_archive_order":6,"of":12,"metrics":{"Accuracy":"66.59"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}