{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PPOA5OXSLVCGRH4ZXDXJRO3A7N","short_pith_number":"pith:PPOA5OXS","schema_version":"1.0","canonical_sha256":"7bdc0ebaf25d44689f99b8ee98bb60fb7dccb352b552c09fd35ac7f299140ad9","source":{"kind":"arxiv","id":"2304.13428","version":1},"attestation_state":"computed","paper":{"title":"Compensation Learning in Semantic Segmentation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bodo Rosenhahn, Christoph Reinders, Timo Kaiser","submitted_at":"2023-04-26T10:26:11Z","abstract_excerpt":"Label noise and ambiguities between similar classes are challenging problems in developing new models and annotating new data for semantic segmentation. In this paper, we propose Compensation Learning in Semantic Segmentation, a framework to identify and compensate ambiguities as well as label noise. More specifically, we add a ground truth depending and globally learned bias to the classification logits and introduce a novel uncertainty branch for neural networks to induce the compensation bias only to relevant regions. Our method is employed into state-of-the-art segmentation frameworks and "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2304.13428","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-26T10:26:11Z","cross_cats_sorted":[],"title_canon_sha256":"79563362ceb1289dbe3946db67e4ce113eb09bcbc741506288e7bb187e102eeb","abstract_canon_sha256":"e051a908663095e61482ec3ee42ff03e785a01cecc908cd392f2424b1e5bb22c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:04:43.930421Z","signature_b64":"LGeGMYXkOeAPA6T7lbdDeA8b1LcdzNIS/qcd3Bh98aEAaeFVtNpPmX/Y0+oQW6lxtnMijxoyYEzz1x3b5/+VDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bdc0ebaf25d44689f99b8ee98bb60fb7dccb352b552c09fd35ac7f299140ad9","last_reissued_at":"2026-07-05T06:04:43.930067Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:04:43.930067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compensation Learning in Semantic Segmentation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bodo Rosenhahn, Christoph Reinders, Timo Kaiser","submitted_at":"2023-04-26T10:26:11Z","abstract_excerpt":"Label noise and ambiguities between similar classes are challenging problems in developing new models and annotating new data for semantic segmentation. In this paper, we propose Compensation Learning in Semantic Segmentation, a framework to identify and compensate ambiguities as well as label noise. More specifically, we add a ground truth depending and globally learned bias to the classification logits and introduce a novel uncertainty branch for neural networks to induce the compensation bias only to relevant regions. Our method is employed into state-of-the-art segmentation frameworks and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.13428","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2304.13428/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2304.13428","created_at":"2026-07-05T06:04:43.930128+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.13428v1","created_at":"2026-07-05T06:04:43.930128+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.13428","created_at":"2026-07-05T06:04:43.930128+00:00"},{"alias_kind":"pith_short_12","alias_value":"PPOA5OXSLVCG","created_at":"2026-07-05T06:04:43.930128+00:00"},{"alias_kind":"pith_short_16","alias_value":"PPOA5OXSLVCGRH4Z","created_at":"2026-07-05T06:04:43.930128+00:00"},{"alias_kind":"pith_short_8","alias_value":"PPOA5OXS","created_at":"2026-07-05T06:04:43.930128+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PPOA5OXSLVCGRH4ZXDXJRO3A7N","json":"https://pith.science/pith/PPOA5OXSLVCGRH4ZXDXJRO3A7N.json","graph_json":"https://pith.science/api/pith-number/PPOA5OXSLVCGRH4ZXDXJRO3A7N/graph.json","events_json":"https://pith.science/api/pith-number/PPOA5OXSLVCGRH4ZXDXJRO3A7N/events.json","paper":"https://pith.science/paper/PPOA5OXS"},"agent_actions":{"view_html":"https://pith.science/pith/PPOA5OXSLVCGRH4ZXDXJRO3A7N","download_json":"https://pith.science/pith/PPOA5OXSLVCGRH4ZXDXJRO3A7N.json","view_paper":"https://pith.science/paper/PPOA5OXS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.13428&json=true","fetch_graph":"https://pith.science/api/pith-number/PPOA5OXSLVCGRH4ZXDXJRO3A7N/graph.json","fetch_events":"https://pith.science/api/pith-number/PPOA5OXSLVCGRH4ZXDXJRO3A7N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PPOA5OXSLVCGRH4ZXDXJRO3A7N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PPOA5OXSLVCGRH4ZXDXJRO3A7N/action/storage_attestation","attest_author":"https://pith.science/pith/PPOA5OXSLVCGRH4ZXDXJRO3A7N/action/author_attestation","sign_citation":"https://pith.science/pith/PPOA5OXSLVCGRH4ZXDXJRO3A7N/action/citation_signature","submit_replication":"https://pith.science/pith/PPOA5OXSLVCGRH4ZXDXJRO3A7N/action/replication_record"}},"created_at":"2026-07-05T06:04:43.930128+00:00","updated_at":"2026-07-05T06:04:43.930128+00:00"}