{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:P237IRUMEYJBZZKU4OJBDPJH63","short_pith_number":"pith:P237IRUM","schema_version":"1.0","canonical_sha256":"7eb7f4468c26121ce554e39211bd27f6dea8a59f1f21243948fb7e7d15158097","source":{"kind":"arxiv","id":"2010.08705","version":1},"attestation_state":"computed","paper":{"title":"DEAL: Difficulty-aware Active Learning for Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Ma, Mingli Song, Shuai Xie, Songtao Sun, Ying Chen, Zunlei Feng","submitted_at":"2020-10-17T03:25:25Z","abstract_excerpt":"Active learning aims to address the paucity of labeled data by finding the most informative samples. However, when applying to semantic segmentation, existing methods ignore the segmentation difficulty of different semantic areas, which leads to poor performance on those hard semantic areas such as tiny or slender objects. To deal with this problem, we propose a semantic Difficulty-awarE Active Learning (DEAL) network composed of two branches: the common segmentation branch and the semantic difficulty branch. For the latter branch, with the supervision of segmentation error between the segment"},"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":"2010.08705","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-10-17T03:25:25Z","cross_cats_sorted":[],"title_canon_sha256":"1f1c647a8b662644585028fa52545bd840525eb0bbbbbbada68b23455cd9e6d6","abstract_canon_sha256":"0167532003cec6e25ff03fc6e1bba409a7146fbc762692c0be3b6b31cc9e01a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:43:44.683189Z","signature_b64":"/29aMK4RYCPFmCizrZNs8C9qIMB02Uxsw2yfYma8uF0gXzBdNKzEn/j8mOSVt38ooeg6KVP+MzQdP/HJcrcTCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7eb7f4468c26121ce554e39211bd27f6dea8a59f1f21243948fb7e7d15158097","last_reissued_at":"2026-07-05T01:43:44.682854Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:43:44.682854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DEAL: Difficulty-aware Active Learning for Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Ma, Mingli Song, Shuai Xie, Songtao Sun, Ying Chen, Zunlei Feng","submitted_at":"2020-10-17T03:25:25Z","abstract_excerpt":"Active learning aims to address the paucity of labeled data by finding the most informative samples. However, when applying to semantic segmentation, existing methods ignore the segmentation difficulty of different semantic areas, which leads to poor performance on those hard semantic areas such as tiny or slender objects. To deal with this problem, we propose a semantic Difficulty-awarE Active Learning (DEAL) network composed of two branches: the common segmentation branch and the semantic difficulty branch. For the latter branch, with the supervision of segmentation error between the segment"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.08705","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/2010.08705/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":"2010.08705","created_at":"2026-07-05T01:43:44.682914+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.08705v1","created_at":"2026-07-05T01:43:44.682914+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.08705","created_at":"2026-07-05T01:43:44.682914+00:00"},{"alias_kind":"pith_short_12","alias_value":"P237IRUMEYJB","created_at":"2026-07-05T01:43:44.682914+00:00"},{"alias_kind":"pith_short_16","alias_value":"P237IRUMEYJBZZKU","created_at":"2026-07-05T01:43:44.682914+00:00"},{"alias_kind":"pith_short_8","alias_value":"P237IRUM","created_at":"2026-07-05T01:43:44.682914+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.16467","citing_title":"Cross-Domain Semantic Segmentation with Large Language Model-Assisted Descriptor Generation","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P237IRUMEYJBZZKU4OJBDPJH63","json":"https://pith.science/pith/P237IRUMEYJBZZKU4OJBDPJH63.json","graph_json":"https://pith.science/api/pith-number/P237IRUMEYJBZZKU4OJBDPJH63/graph.json","events_json":"https://pith.science/api/pith-number/P237IRUMEYJBZZKU4OJBDPJH63/events.json","paper":"https://pith.science/paper/P237IRUM"},"agent_actions":{"view_html":"https://pith.science/pith/P237IRUMEYJBZZKU4OJBDPJH63","download_json":"https://pith.science/pith/P237IRUMEYJBZZKU4OJBDPJH63.json","view_paper":"https://pith.science/paper/P237IRUM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.08705&json=true","fetch_graph":"https://pith.science/api/pith-number/P237IRUMEYJBZZKU4OJBDPJH63/graph.json","fetch_events":"https://pith.science/api/pith-number/P237IRUMEYJBZZKU4OJBDPJH63/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P237IRUMEYJBZZKU4OJBDPJH63/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P237IRUMEYJBZZKU4OJBDPJH63/action/storage_attestation","attest_author":"https://pith.science/pith/P237IRUMEYJBZZKU4OJBDPJH63/action/author_attestation","sign_citation":"https://pith.science/pith/P237IRUMEYJBZZKU4OJBDPJH63/action/citation_signature","submit_replication":"https://pith.science/pith/P237IRUMEYJBZZKU4OJBDPJH63/action/replication_record"}},"created_at":"2026-07-05T01:43:44.682914+00:00","updated_at":"2026-07-05T01:43:44.682914+00:00"}