{"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/mfnet-multi-class-few-shot-segmentation","title":"MFNet: Multi-class Few-shot Segmentation Network with Pixel-wise Metric Learning","arxiv_id":"2111.00232","date":"2021-10-30","proceeding":null,"authors":["Miao Zhang","Miaojing Shi","Li Li"],"abstract":"In visual recognition tasks, few-shot learning requires the ability to learn object categories with few support examples. Its re-popularity in light of the deep learning development is mainly in image classification. This work focuses on few-shot semantic segmentation, which is still a largely unexplored field. A few recent advances are often restricted to single-class few-shot segmentation. In this paper, we first present a novel multi-way (class) encoding and decoding architecture which effectively fuses multi-scale query information and multi-class support information into one query-support embedding. Multi-class segmentation is directly decoded upon this embedding. For better feature fusion, a multi-level attention mechanism is proposed within the architecture, which includes the attention for support feature modulation and attention for multi-scale combination. Last, to enhance the embedding space learning, an additional pixel-wise metric learning module is introduced with triplet loss formulated on the pixel-level embedding of the input image. Extensive experiments on standard benchmarks PASCAL-5i and COCO-20i show clear benefits of our method over the state of the art in few-shot segmentation","url_abs":"https://arxiv.org/abs/2111.00232v4","url_pdf":"https://arxiv.org/pdf/2111.00232v4.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-learning","task_name":"Few-Shot Learning"},{"task_slug":"few-shot-image-segmentation","task_name":"Few-Shot Semantic Segmentation"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":null,"task_name":"Triplet"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"triplet-loss","method_name":"Triplet Loss"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-semantic-segmentation-on-coco-20i-2-1","task":"Few-Shot Semantic Segmentation","dataset":"COCO-20i (2-way 1-shot)","model":"MFNet (ResNet-50)","rank_in_archive_order":4,"of":6,"metrics":{"mIoU":"24.1"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2111.00232","atlas_url":"https://app.syntology.ai/?focus=2111.00232","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}