{"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/sill-net-feature-augmentation-with-separated","title":"Sill-Net: Feature Augmentation with Separated Illumination Representation","arxiv_id":"2102.03539","date":"2021-02-06","proceeding":null,"authors":["Haipeng Zhang","Zhong Cao","Ziang Yan","ChangShui Zhang"],"abstract":"For visual object recognition tasks, the illumination variations can cause distinct changes in object appearance and thus confuse the deep neural network based recognition models. Especially for some rare illumination conditions, collecting sufficient training samples could be time-consuming and expensive. To solve this problem, in this paper we propose a novel neural network architecture called Separating-Illumination Network (Sill-Net). Sill-Net learns to separate illumination features from images, and then during training we augment training samples with these separated illumination features in the feature space. Experimental results demonstrate that our approach outperforms current state-of-the-art methods in several object classification benchmarks.","url_abs":"https://arxiv.org/abs/2102.03539v3","url_pdf":"https://arxiv.org/pdf/2102.03539v3.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":"sill-net-feature-augmentation-with-separated","repo_url":"https://github.com/lanfenghuanyu/Sill-Net","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"few-shot-image-classification","task_name":"Few-Shot Image Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"traffic-sign-recognition","task_name":"Traffic Sign Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-image-classification-on-cifar-fs-5","task":"Few-Shot Image Classification","dataset":"CIFAR-FS 5-way (1-shot)","model":"Illumination Augmentation","rank_in_archive_order":5,"of":38,"metrics":{"Accuracy":"87.73"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-cifar-fs-5-1","task":"Few-Shot Image Classification","dataset":"CIFAR-FS 5-way (5-shot)","model":"Illumination Augmentation","rank_in_archive_order":6,"of":39,"metrics":{"Accuracy":"91.09"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-cub-200-5-1","task":"Few-Shot Image Classification","dataset":"CUB 200 5-way 1-shot","model":"Illumination Augmentation","rank_in_archive_order":6,"of":36,"metrics":{"Accuracy":"94.73"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-cub-200-5","task":"Few-Shot Image Classification","dataset":"CUB 200 5-way 5-shot","model":"Illumination Augmentation","rank_in_archive_order":5,"of":32,"metrics":{"Accuracy":"96.28"},"uses_additional_data":true},{"leaderboard":"/sota/few-shot-image-classification-on-mini-2","task":"Few-Shot Image Classification","dataset":"Mini-Imagenet 5-way (1-shot)","model":"Illumination Augmentation","rank_in_archive_order":11,"of":105,"metrics":{"Accuracy":"82.99"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-mini-3","task":"Few-Shot Image Classification","dataset":"Mini-Imagenet 5-way (5-shot)","model":"Illumination Augmentation","rank_in_archive_order":13,"of":95,"metrics":{"Accuracy":"89.14"},"uses_additional_data":false},{"leaderboard":"/sota/traffic-sign-recognition-on-belgalogos","task":"Traffic Sign Recognition","dataset":"BelgaLogos","model":"Sill-Net","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"89.48"},"uses_additional_data":false},{"leaderboard":"/sota/traffic-sign-recognition-on-belgian-traffic","task":"Traffic Sign Recognition","dataset":"Belgian Traffic Sign Classification","model":"Sill-Net","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"98.97"},"uses_additional_data":false},{"leaderboard":"/sota/traffic-sign-recognition-on-chinese-traffic","task":"Traffic Sign Recognition","dataset":"Chinese Traffic Sign Database","model":"Sill-Net","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"97.19"},"uses_additional_data":false},{"leaderboard":"/sota/traffic-sign-recognition-on-flickrlogos-32","task":"Traffic Sign Recognition","dataset":"FlickrLogos-32","model":"Sill-Net","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"95.80"},"uses_additional_data":false},{"leaderboard":"/sota/traffic-sign-recognition-on-gtsrb","task":"Traffic Sign Recognition","dataset":"GTSRB","model":"Sill-Net","rank_in_archive_order":2,"of":5,"metrics":{"Accuracy":"99.68%"},"uses_additional_data":false},{"leaderboard":"/sota/traffic-sign-recognition-on-toplogo-10","task":"Traffic Sign Recognition","dataset":"TopLogo-10","model":"Sill-Net","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"89.66"},"uses_additional_data":false},{"leaderboard":"/sota/traffic-sign-recognition-on-tsinghua-tencent","task":"Traffic Sign Recognition","dataset":"Tsinghua-Tencent 100K","model":"Sill-Net","rank_in_archive_order":6,"of":6,"metrics":{"Accuracy":"99.53"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2102.03539","atlas_url":"https://app.syntology.ai/?focus=2102.03539","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}