{"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/detecting-the-unexpected-via-image","title":"Detecting the Unexpected via Image Resynthesis","arxiv_id":"1904.07595","date":"2019-04-16","proceeding":"ICCV 2019 10","authors":["Krzysztof Lis","Krishna Nakka","Pascal Fua","Mathieu Salzmann"],"abstract":"Classical semantic segmentation methods, including the recent deep learning\nones, assume that all classes observed at test time have been seen during\ntraining. In this paper, we tackle the more realistic scenario where unexpected\nobjects of unknown classes can appear at test time. The main trends in this\narea either leverage the notion of prediction uncertainty to flag the regions\nwith low confidence as unknown, or rely on autoencoders and highlight\npoorly-decoded regions. Having observed that, in both cases, the detected\nregions typically do not correspond to unexpected objects, in this paper, we\nintroduce a drastically different strategy: It relies on the intuition that the\nnetwork will produce spurious labels in regions depicting unexpected objects.\nTherefore, resynthesizing the image from the resulting semantic map will yield\nsignificant appearance differences with respect to the input image. In other\nwords, we translate the problem of detecting unknown classes to one of\nidentifying poorly-resynthesized image regions. We show that this outperforms\nboth uncertainty- and autoencoder-based methods.","url_abs":"http://arxiv.org/abs/1904.07595v2","url_pdf":"http://arxiv.org/pdf/1904.07595v2.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":"detecting-the-unexpected-via-image","repo_url":"https://github.com/cvlab-epfl/detecting-the-unexpected","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"torch","reach":null},{"paper_slug":"detecting-the-unexpected-via-image","repo_url":"https://github.com/adynathos/LabelGrab","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"detecting-the-unexpected-via-image","repo_url":"https://github.com/cvlab-epfl/LabelGrab","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"resynthesis","task_name":"Resynthesis"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[{"slug":"road-anomaly","name":"Road Anomaly","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1904.07595","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.07595"}},"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/cvlab-epfl/detecting-the-unexpected","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cvlab-epfl/LabelGrab","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/adynathos/LabelGrab","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"8c13881a66200b7d","entry":"experiment_class_by_path","repo":"cvlab-epfl/detecting-the-unexpected","repo_kind":"official","path":"src/pipeline/experiment.py","file_url":"https://github.com/cvlab-epfl/detecting-the-unexpected/blob/HEAD/src/pipeline/experiment.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":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"8c13881a66200b7d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}