{"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/resolving-semantic-confusions-for-improved-1","title":"Resolving Semantic Confusions for Improved Zero-Shot Detection","arxiv_id":"2212.06097","date":"2022-12-12","proceeding":"British Machine Vision Conference 2022 11","authors":["Sandipan Sarma","Sushil Kumar","Arijit Sur"],"abstract":"Zero-shot detection (ZSD) is a challenging task where we aim to recognize and localize objects simultaneously, even when our model has not been trained with visual samples of a few target (\"unseen\") classes. Recently, methods employing generative models like GANs have shown some of the best results, where unseen-class samples are generated based on their semantics by a GAN trained on seen-class data, enabling vanilla object detectors to recognize unseen objects. However, the problem of semantic confusion still remains, where the model is sometimes unable to distinguish between semantically-similar classes. In this work, we propose to train a generative model incorporating a triplet loss that acknowledges the degree of dissimilarity between classes and reflects them in the generated samples. Moreover, a cyclic-consistency loss is also enforced to ensure that generated visual samples of a class highly correspond to their own semantics. Extensive experiments on two benchmark ZSD datasets - MSCOCO and PASCAL-VOC - demonstrate significant gains over the current ZSD methods, reducing semantic confusion and improving detection for the unseen classes.","url_abs":"https://arxiv.org/abs/2212.06097v1","url_pdf":"https://arxiv.org/pdf/2212.06097v1.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":"resolving-semantic-confusions-for-improved-1","repo_url":"https://github.com/sandipan211/ZSD-SC-Resolver","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"generalized-zero-shot-object-detection","task_name":"Generalized Zero-Shot Object Detection"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":null,"task_name":"Triplet"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"},{"task_slug":"zero-shot-object-detection","task_name":"Zero-Shot Object Detection"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"faster-r-cnn","method_name":"Faster R-CNN"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"roipool","method_name":"RoIPool"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"triplet-loss","method_name":"Triplet Loss"},{"method_slug":"wgan","method_name":"WGAN"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/zero-shot-object-detection-on-ms-coco","task":"Zero-Shot Object Detection","dataset":"MS-COCO","model":"ZSD-SCR","rank_in_archive_order":3,"of":9,"metrics":{"Recall":"65.10","mAP":"20.10"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-object-detection-on-pascal-voc-07","task":"Zero-Shot Object Detection","dataset":"PASCAL VOC'07","model":"ZSD-SCR","rank_in_archive_order":4,"of":7,"metrics":{"mAP":"62.70"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2212.06097","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}