{"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/pixel-wise-energy-biased-abstention-learning","title":"Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenes","arxiv_id":"2111.12264","date":"2021-11-24","proceeding":null,"authors":["Yu Tian","Yuyuan Liu","Guansong Pang","Fengbei Liu","Yuanhong Chen","Gustavo Carneiro"],"abstract":"State-of-the-art (SOTA) anomaly segmentation approaches on complex urban driving scenes explore pixel-wise classification uncertainty learned from outlier exposure, or external reconstruction models. However, previous uncertainty approaches that directly associate high uncertainty to anomaly may sometimes lead to incorrect anomaly predictions, and external reconstruction models tend to be too inefficient for real-time self-driving embedded systems. In this paper, we propose a new anomaly segmentation method, named pixel-wise energy-biased abstention learning (PEBAL), that explores pixel-wise abstention learning (AL) with a model that learns an adaptive pixel-level anomaly class, and an energy-based model (EBM) that learns inlier pixel distribution. More specifically, PEBAL is based on a non-trivial joint training of EBM and AL, where EBM is trained to output high-energy for anomaly pixels (from outlier exposure) and AL is trained such that these high-energy pixels receive adaptive low penalty for being included to the anomaly class. We extensively evaluate PEBAL against the SOTA and show that it achieves the best performance across four benchmarks. Code is available at https://github.com/tianyu0207/PEBAL.","url_abs":"https://arxiv.org/abs/2111.12264v6","url_pdf":"https://arxiv.org/pdf/2111.12264v6.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":"pixel-wise-energy-biased-abstention-learning","repo_url":"https://github.com/tianyu0207/pebal","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"pixel-wise-energy-biased-abstention-learning","repo_url":"https://github.com/gaozhitong/atta","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"pixel-wise-energy-biased-abstention-learning","repo_url":"https://github.com/yyliu01/rpl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"anomaly-segmentation","task_name":"Anomaly Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"ebm","method_name":"EBM"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/anomaly-detection-on-fishyscapes-1","task":"Anomaly Detection","dataset":"Fishyscapes","model":"PEBAL","rank_in_archive_order":3,"of":8,"metrics":{"AP":"92.38","FPR95":"1.73"},"uses_additional_data":true},{"leaderboard":"/sota/anomaly-detection-on-fishyscapes-l-f","task":"Anomaly Detection","dataset":"Fishyscapes L&F","model":"PEBAL","rank_in_archive_order":7,"of":18,"metrics":{"AP":"44.17","FPR95":"7.58"},"uses_additional_data":true},{"leaderboard":"/sota/anomaly-detection-on-lost-and-found","task":"Anomaly Detection","dataset":"Lost and Found","model":"PEBAL","rank_in_archive_order":2,"of":4,"metrics":{"AP":"78.29","FPR":"0.81"},"uses_additional_data":true},{"leaderboard":"/sota/anomaly-detection-on-road-anomaly","task":"Anomaly Detection","dataset":"Road Anomaly","model":"PEBAL","rank_in_archive_order":7,"of":10,"metrics":{"AP":"45.10","FPR95":"44.58"},"uses_additional_data":true}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2111.12264","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.12264"}},"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/yyliu01/rpl","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tianyu0207/pebal","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gaozhitong/atta","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"5a9287644e6cb57d","entry":"calc_precision_recall","repo":"tianyu0207/pebal","repo_kind":"official","path":"code/utils/pyt_utils.py","file_url":"https://github.com/tianyu0207/pebal/blob/HEAD/code/utils/pyt_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5a9287644e6cb57d"}},{"code_sha256_prefix":"9a1506ccd1761596","entry":"calc_sensitivity_specificity","repo":"tianyu0207/pebal","repo_kind":"official","path":"code/utils/pyt_utils.py","file_url":"https://github.com/tianyu0207/pebal/blob/HEAD/code/utils/pyt_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9a1506ccd1761596"}},{"code_sha256_prefix":"c753c3835ef3486f","entry":"counts_array_to_data_list","repo":"tianyu0207/pebal","repo_kind":"official","path":"code/utils/pyt_utils.py","file_url":"https://github.com/tianyu0207/pebal/blob/HEAD/code/utils/pyt_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c753c3835ef3486f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}