{"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/a-strong-baseline-for-generalized-few-shot","title":"A Strong Baseline for Generalized Few-Shot Semantic Segmentation","arxiv_id":"2211.14126","date":"2022-11-25","proceeding":"CVPR 2023 1","authors":["Sina Hajimiri","Malik Boudiaf","Ismail Ben Ayed","Jose Dolz"],"abstract":"This paper introduces a generalized few-shot segmentation framework with a straightforward training process and an easy-to-optimize inference phase. In particular, we propose a simple yet effective model based on the well-known InfoMax principle, where the Mutual Information (MI) between the learned feature representations and their corresponding predictions is maximized. In addition, the terms derived from our MI-based formulation are coupled with a knowledge distillation term to retain the knowledge on base classes. With a simple training process, our inference model can be applied on top of any segmentation network trained on base classes. The proposed inference yields substantial improvements on the popular few-shot segmentation benchmarks, PASCAL-$5^i$ and COCO-$20^i$. Particularly, for novel classes, the improvement gains range from 7% to 26% (PASCAL-$5^i$) and from 3% to 12% (COCO-$20^i$) in the 1-shot and 5-shot scenarios, respectively. Furthermore, we propose a more challenging setting, where performance gaps are further exacerbated. Our code is publicly available at https://github.com/sinahmr/DIaM.","url_abs":"https://arxiv.org/abs/2211.14126v2","url_pdf":"https://arxiv.org/pdf/2211.14126v2.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":"a-strong-baseline-for-generalized-few-shot","repo_url":"https://github.com/sinahmr/diam","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-strong-baseline-for-generalized-few-shot","repo_url":"https://github.com/cliffbb/oem-fewshot-challenge","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"few-shot-image-segmentation","task_name":"Few-Shot Semantic Segmentation"},{"task_slug":"generalized-few-shot-semantic-segmentation","task_name":"Generalized Few-Shot Semantic Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"auxiliary-classifier","method_name":"Auxiliary Classifier"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dilated-convolution","method_name":"Dilated Convolution"},{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"},{"method_slug":"pspnet","method_name":"PSPNet"},{"method_slug":"pyramid-pooling-module","method_name":"Pyramid Pooling Module"},{"method_slug":"relu","method_name":"ReLU"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/generalized-few-shot-semantic-segmentation-on-2","task":"Generalized Few-Shot Semantic Segmentation","dataset":"COCO-20i (1-shot)","model":"DIaM (ResNet-50)","rank_in_archive_order":4,"of":6,"metrics":{"Mean Base and Novel":"32.75","Mean IoU":"40.52"},"uses_additional_data":false},{"leaderboard":"/sota/generalized-few-shot-semantic-segmentation-on-3","task":"Generalized Few-Shot Semantic Segmentation","dataset":"COCO-20i (5-shot)","model":"DIaM (ResNet-50)","rank_in_archive_order":4,"of":5,"metrics":{"Mean Base and Novel":"38.55","Mean IoU":"43.46"},"uses_additional_data":false},{"leaderboard":"/sota/generalized-few-shot-semantic-segmentation-on","task":"Generalized Few-Shot Semantic Segmentation","dataset":"PASCAL-5i (1-Shot)","model":"DIaM (ResNet-50)","rank_in_archive_order":4,"of":5,"metrics":{"Mean Base and Novel":"53","Mean IoU":"61.95"},"uses_additional_data":false},{"leaderboard":"/sota/generalized-few-shot-semantic-segmentation-on-1","task":"Generalized Few-Shot Semantic Segmentation","dataset":"PASCAL-5i (5-Shot)","model":"DIaM (ResNet-50)","rank_in_archive_order":4,"of":6,"metrics":{"Mean Base and Novel":"63.08","Mean IoU":"66.97"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2211.14126","atlas_url":"https://app.syntology.ai/?focus=2211.14126","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}