{"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/normalizing-flow-based-feature-synthesis-for","title":"Normalizing Flow based Feature Synthesis for Outlier-Aware Object Detection","arxiv_id":"2302.07106","date":"2023-02-01","proceeding":"CVPR 2023 1","authors":["Nishant Kumar","Siniša Šegvić","Abouzar Eslami","Stefan Gumhold"],"abstract":"Real-world deployment of reliable object detectors is crucial for applications such as autonomous driving. However, general-purpose object detectors like Faster R-CNN are prone to providing overconfident predictions for outlier objects. Recent outlier-aware object detection approaches estimate the density of instance-wide features with class-conditional Gaussians and train on synthesized outlier features from their low-likelihood regions. However, this strategy does not guarantee that the synthesized outlier features will have a low likelihood according to the other class-conditional Gaussians. We propose a novel outlier-aware object detection framework that distinguishes outliers from inlier objects by learning the joint data distribution of all inlier classes with an invertible normalizing flow. The appropriate sampling of the flow model ensures that the synthesized outliers have a lower likelihood than inliers of all object classes, thereby modeling a better decision boundary between inlier and outlier objects. Our approach significantly outperforms the state-of-the-art for outlier-aware object detection on both image and video datasets. Code available at https://github.com/nish03/FFS","url_abs":"https://arxiv.org/abs/2302.07106v3","url_pdf":"https://arxiv.org/pdf/2302.07106v3.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":"normalizing-flow-based-feature-synthesis-for","repo_url":"https://github.com/nish03/ffs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"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":"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"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2302.07106","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.07106"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nish03/ffs","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"ran_honours":1,"unverified":2},"by_repo_kind":{"official":{"samples":4,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"573ab018aa3f2e6f","entry":"permute_to_N_HWA_K","repo":"nish03/ffs","repo_kind":"official","path":"Flow-Feature-Synthesis/detection/inference/retinanet_predictor.py","file_url":"https://github.com/nish03/ffs/blob/HEAD/Flow-Feature-Synthesis/detection/inference/retinanet_predictor.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"573ab018aa3f2e6f"}},{"code_sha256_prefix":"d4acb3120a027622","entry":"stable_cumsum","repo":"nish03/ffs","repo_kind":"official","path":"Flow-Feature-Synthesis/detection/metric_utils.py","file_url":"https://github.com/nish03/ffs/blob/HEAD/Flow-Feature-Synthesis/detection/metric_utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d4acb3120a027622"}},{"code_sha256_prefix":"1e4534a223543409","entry":"fpr_and_fdr_at_recall","repo":"nish03/ffs","repo_kind":"official","path":"Flow-Feature-Synthesis/detection/metric_utils.py","file_url":"https://github.com/nish03/ffs/blob/HEAD/Flow-Feature-Synthesis/detection/metric_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1e4534a223543409"}},{"code_sha256_prefix":"d9461049c5aa79fc","entry":"get_measures","repo":"nish03/ffs","repo_kind":"official","path":"Flow-Feature-Synthesis/detection/metric_utils.py","file_url":"https://github.com/nish03/ffs/blob/HEAD/Flow-Feature-Synthesis/detection/metric_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d9461049c5aa79fc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}