{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QOU2EGF5XX4QLHIXVAW25GTUHL","short_pith_number":"pith:QOU2EGF5","schema_version":"1.0","canonical_sha256":"83a9a218bdbdf9059d17a82dae9a743ae0eebbf0d94434234669afe03e8c5b08","source":{"kind":"arxiv","id":"2102.04566","version":1},"attestation_state":"computed","paper":{"title":"Semantic Segmentation with Labeling Uncertainty and Class Imbalance","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daniel Matte Freitas, Diogo Nunes Gon\\c{c}alves, Jonathan de Andrade Silva, Jonathan Li, Jos\\'e Augusto Correa Martins, Jos\\'e Marcato Junior, Lucas Prado Osco, Patrik Ol\\~a Bressan, Raymundo Cordero Garcia, Wesley Nunes Gon\\c{c}alves, Zhipeng Luo","submitted_at":"2021-02-08T22:53:33Z","abstract_excerpt":"Recently, methods based on Convolutional Neural Networks (CNN) achieved impressive success in semantic segmentation tasks. However, challenges such as the class imbalance and the uncertainty in the pixel-labeling process are not completely addressed. As such, we present a new approach that calculates a weight for each pixel considering its class and uncertainty during the labeling process. The pixel-wise weights are used during training to increase or decrease the importance of the pixels. Experimental results show that the proposed approach leads to significant improvements in three challengi"},"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":"2102.04566","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-08T22:53:33Z","cross_cats_sorted":[],"title_canon_sha256":"0c64a342b0460c7c0603291235ad5616568f9790605e33d9c3f74047c6e0e744","abstract_canon_sha256":"84b08ea401782890b7c198572cff72e617144c49e7c1a843dbdead6c2394be3a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:27:04.762408Z","signature_b64":"CL/X9awaKxttYNe626IE5blf60RMpTKkeMC4zqVN1ENAkIMeJNX4z5cmeZzEd5iTUoW0YLjcnrW18oTtRdQ/CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83a9a218bdbdf9059d17a82dae9a743ae0eebbf0d94434234669afe03e8c5b08","last_reissued_at":"2026-07-05T04:27:04.761953Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:27:04.761953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantic Segmentation with Labeling Uncertainty and Class Imbalance","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daniel Matte Freitas, Diogo Nunes Gon\\c{c}alves, Jonathan de Andrade Silva, Jonathan Li, Jos\\'e Augusto Correa Martins, Jos\\'e Marcato Junior, Lucas Prado Osco, Patrik Ol\\~a Bressan, Raymundo Cordero Garcia, Wesley Nunes Gon\\c{c}alves, Zhipeng Luo","submitted_at":"2021-02-08T22:53:33Z","abstract_excerpt":"Recently, methods based on Convolutional Neural Networks (CNN) achieved impressive success in semantic segmentation tasks. However, challenges such as the class imbalance and the uncertainty in the pixel-labeling process are not completely addressed. As such, we present a new approach that calculates a weight for each pixel considering its class and uncertainty during the labeling process. The pixel-wise weights are used during training to increase or decrease the importance of the pixels. Experimental results show that the proposed approach leads to significant improvements in three challengi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.04566","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/2102.04566/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":"2102.04566","created_at":"2026-07-05T04:27:04.762008+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.04566v1","created_at":"2026-07-05T04:27:04.762008+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.04566","created_at":"2026-07-05T04:27:04.762008+00:00"},{"alias_kind":"pith_short_12","alias_value":"QOU2EGF5XX4Q","created_at":"2026-07-05T04:27:04.762008+00:00"},{"alias_kind":"pith_short_16","alias_value":"QOU2EGF5XX4QLHIX","created_at":"2026-07-05T04:27:04.762008+00:00"},{"alias_kind":"pith_short_8","alias_value":"QOU2EGF5","created_at":"2026-07-05T04:27:04.762008+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/QOU2EGF5XX4QLHIXVAW25GTUHL","json":"https://pith.science/pith/QOU2EGF5XX4QLHIXVAW25GTUHL.json","graph_json":"https://pith.science/api/pith-number/QOU2EGF5XX4QLHIXVAW25GTUHL/graph.json","events_json":"https://pith.science/api/pith-number/QOU2EGF5XX4QLHIXVAW25GTUHL/events.json","paper":"https://pith.science/paper/QOU2EGF5"},"agent_actions":{"view_html":"https://pith.science/pith/QOU2EGF5XX4QLHIXVAW25GTUHL","download_json":"https://pith.science/pith/QOU2EGF5XX4QLHIXVAW25GTUHL.json","view_paper":"https://pith.science/paper/QOU2EGF5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.04566&json=true","fetch_graph":"https://pith.science/api/pith-number/QOU2EGF5XX4QLHIXVAW25GTUHL/graph.json","fetch_events":"https://pith.science/api/pith-number/QOU2EGF5XX4QLHIXVAW25GTUHL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QOU2EGF5XX4QLHIXVAW25GTUHL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QOU2EGF5XX4QLHIXVAW25GTUHL/action/storage_attestation","attest_author":"https://pith.science/pith/QOU2EGF5XX4QLHIXVAW25GTUHL/action/author_attestation","sign_citation":"https://pith.science/pith/QOU2EGF5XX4QLHIXVAW25GTUHL/action/citation_signature","submit_replication":"https://pith.science/pith/QOU2EGF5XX4QLHIXVAW25GTUHL/action/replication_record"}},"created_at":"2026-07-05T04:27:04.762008+00:00","updated_at":"2026-07-05T04:27:04.762008+00:00"}