{"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/multi-level-metric-learning-for-few-shot","title":"Multi-level Metric Learning for Few-shot Image Recognition","arxiv_id":"2103.11383","date":"2021-03-21","proceeding":null,"authors":["Haoxing Chen","Huaxiong Li","Yaohui Li","Chunlin Chen"],"abstract":"Few-shot learning is devoted to training a model on few samples. Most of these approaches learn a model based on a pixel-level or global-level feature representation. However, using global features may lose local information, and using pixel-level features may lose the contextual semantics of the image. Moreover, such works can only measure the relations between them on a single level, which is not comprehensive and effective. And if query images can simultaneously be well classified via three distinct level similarity metrics, the query images within a class can be more tightly distributed in a smaller feature space, generating more discriminative feature maps. Motivated by this, we propose a novel Part-level Embedding Adaptation with Graph (PEAG) method to generate task-specific features. Moreover, a Multi-level Metric Learning (MML) method is proposed, which not only calculates the pixel-level similarity but also considers the similarity of part-level features and global-level features. Extensive experiments on popular few-shot image recognition datasets prove the effectiveness of our method compared with the state-of-the-art methods. Our code is available at \\url{https://github.com/chenhaoxing/M2L}.","url_abs":"https://arxiv.org/abs/2103.11383v4","url_pdf":"https://arxiv.org/pdf/2103.11383v4.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":[],"tasks":[{"task_slug":"few-shot-image-classification","task_name":"Few-Shot Image Classification"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"metric-learning","task_name":"Metric Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-image-classification-on-stanford-2","task":"Few-Shot Image Classification","dataset":"Stanford Cars 5-way (1-shot)","model":"MML(KL)","rank_in_archive_order":2,"of":6,"metrics":{"Accuracy":"72.43"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-stanford-3","task":"Few-Shot Image Classification","dataset":"Stanford Cars 5-way (5-shot)","model":"MML(KL)","rank_in_archive_order":2,"of":6,"metrics":{"Accuracy":"91.05"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-stanford","task":"Few-Shot Image Classification","dataset":"Stanford Dogs 5-way (1-shot)","model":"MML(KL)","rank_in_archive_order":1,"of":3,"metrics":{"Accuracy":"59.05"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-stanford-1","task":"Few-Shot Image Classification","dataset":"Stanford Dogs 5-way (5-shot)","model":"MML(KL)","rank_in_archive_order":1,"of":6,"metrics":{"Accuracy":"75.59"},"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}