{"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/robust-and-accurate-object-detection-via","title":"Robust and Accurate Object Detection via Adversarial Learning","arxiv_id":"2103.13886","date":"2021-03-23","proceeding":"CVPR 2021 1","authors":["Xiangning Chen","Cihang Xie","Mingxing Tan","Li Zhang","Cho-Jui Hsieh","Boqing Gong"],"abstract":"Data augmentation has become a de facto component for training high-performance deep image classifiers, but its potential is under-explored for object detection. Noting that most state-of-the-art object detectors benefit from fine-tuning a pre-trained classifier, we first study how the classifiers' gains from various data augmentations transfer to object detection. The results are discouraging; the gains diminish after fine-tuning in terms of either accuracy or robustness. This work instead augments the fine-tuning stage for object detectors by exploring adversarial examples, which can be viewed as a model-dependent data augmentation. Our method dynamically selects the stronger adversarial images sourced from a detector's classification and localization branches and evolves with the detector to ensure the augmentation policy stays current and relevant. This model-dependent augmentation generalizes to different object detectors better than AutoAugment, a model-agnostic augmentation policy searched based on one particular detector. Our approach boosts the performance of state-of-the-art EfficientDets by +1.1 mAP on the COCO object detection benchmark. It also improves the detectors' robustness against natural distortions by +3.8 mAP and against domain shift by +1.3 mAP. Models are available at https://github.com/google/automl/tree/master/efficientdet/Det-AdvProp.md","url_abs":"https://arxiv.org/abs/2103.13886v2","url_pdf":"https://arxiv.org/pdf/2103.13886v2.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":"robust-and-accurate-object-detection-via","repo_url":"https://github.com/google/automl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"robust-and-accurate-object-detection-via","repo_url":"https://github.com/MindSpore-scientific-2/code-4/tree/main/fisheradversarial-mindspore","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"robust-and-accurate-object-detection-via","repo_url":"https://github.com/MindSpore-scientific-2/code-5/tree/main/fisheradversarial-mindspore","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"automl","task_name":"AutoML"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"autoaugment","method_name":"AutoAugment"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/object-detection-on-coco-o","task":"Object Detection","dataset":"COCO-O","model":"Det-AdvProp\n(EfficientNet-B5)","rank_in_archive_order":17,"of":45,"metrics":{"Average mAP":"30.8","Effective Robustness":"7.34"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2103.13886","atlas_url":"https://app.syntology.ai/?focus=2103.13886","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}