{"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/application-of-decision-rules-for-handling","title":"Application of Decision Rules for Handling Class Imbalance in Semantic Segmentation","arxiv_id":"1901.08394","date":"2019-01-24","proceeding":null,"authors":["Robin Chan","Matthias Rottmann","Fabian Hüger","Peter Schlicht","Hanno Gottschalk"],"abstract":"As part of autonomous car driving systems, semantic segmentation is an\nessential component to obtain a full understanding of the car's environment.\nOne difficulty, that occurs while training neural networks for this purpose, is\nclass imbalance of training data. Consequently, a neural network trained on\nunbalanced data in combination with maximum a-posteriori classification may\neasily ignore classes that are rare in terms of their frequency in the dataset.\nHowever, these classes are often of highest interest. We approach such\npotential misclassifications by weighting the posterior class probabilities\nwith the prior class probabilities which in our case are the inverse\nfrequencies of the corresponding classes in the training dataset. More\nprecisely, we adopt a localized method by computing the priors pixel-wise such\nthat the impact can be analyzed at pixel level as well. In our experiments, we\ntrain one network from scratch using a proprietary dataset containing 20,000\nannotated frames of video sequences recorded from street scenes. The evaluation\non our test set shows an increase of average recall with regard to instances of\npedestrians and info signs by $25\\%$ and $23.4\\%$, respectively. In addition,\nwe significantly reduce the non-detection rate for instances of the same\nclasses by $61\\%$ and $38\\%$.","url_abs":"http://arxiv.org/abs/1901.08394v1","url_pdf":"http://arxiv.org/pdf/1901.08394v1.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":"application-of-decision-rules-for-handling","repo_url":"https://github.com/robin-chan/decision-rules","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"info","method_name":"INFO"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.08394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.08394"}},"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/robin-chan/decision-rules","reach":null}],"summary":{"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"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":2,"samples":[{"code_sha256_prefix":"442a2012d75c4821","entry":"softmax","repo":"robin-chan/decision-rules","repo_kind":"official","path":"scripts-predict/predict.py","file_url":"https://github.com/robin-chan/decision-rules/blob/HEAD/scripts-predict/predict.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"442a2012d75c4821"}},{"code_sha256_prefix":"4fa6717c9d8a2be2","entry":"prediction","repo":"robin-chan/decision-rules","repo_kind":"official","path":"scripts-predict/predict.py","file_url":"https://github.com/robin-chan/decision-rules/blob/HEAD/scripts-predict/predict.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4fa6717c9d8a2be2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}