{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:7CVWKOPRB7TV4ZJ4LYI226U2IX","short_pith_number":"pith:7CVWKOPR","schema_version":"1.0","canonical_sha256":"f8ab6539f10fe75e653c5e11ad7a9a45d0a6ebb18f95da2144818fc6f78269df","source":{"kind":"arxiv","id":"2010.12023","version":1},"attestation_state":"computed","paper":{"title":"Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dong Huang, Vijayakumar Bhagavatula, Yang Zou, Zeyi Huang","submitted_at":"2020-10-22T20:13:32Z","abstract_excerpt":"Weakly Supervised Object Detection (WSOD) has emerged as an effective tool to train object detectors using only the image-level category labels. However, without object-level labels, WSOD detectors are prone to detect bounding boxes on salient objects, clustered objects and discriminative object parts. Moreover, the image-level category labels do not enforce consistent object detection across different transformations of the same images. To address the above issues, we propose a Comprehensive Attention Self-Distillation (CASD) training approach for WSOD. To balance feature learning among all o"},"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":"2010.12023","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-10-22T20:13:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0088f792bf0fc5a6a98a11b85a8dc5f690b20471b5f9febd6ff0ffb55dd9c5fe","abstract_canon_sha256":"19f53e237c26959255c19a134b82204f8b151abf5ad5f554734f96085d6edf21"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:32.899528Z","signature_b64":"K7OkYmvLfnN+DCpRrFdP/8pjzt8ZFysMZw7JmjN6ckFLkFPQfLAVBWZ10QJmK9+914fVq7znSCCfUdm8/lOQBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8ab6539f10fe75e653c5e11ad7a9a45d0a6ebb18f95da2144818fc6f78269df","last_reissued_at":"2026-07-05T01:45:32.899043Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:32.899043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dong Huang, Vijayakumar Bhagavatula, Yang Zou, Zeyi Huang","submitted_at":"2020-10-22T20:13:32Z","abstract_excerpt":"Weakly Supervised Object Detection (WSOD) has emerged as an effective tool to train object detectors using only the image-level category labels. However, without object-level labels, WSOD detectors are prone to detect bounding boxes on salient objects, clustered objects and discriminative object parts. Moreover, the image-level category labels do not enforce consistent object detection across different transformations of the same images. To address the above issues, we propose a Comprehensive Attention Self-Distillation (CASD) training approach for WSOD. To balance feature learning among all o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12023","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/2010.12023/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":"2010.12023","created_at":"2026-07-05T01:45:32.899099+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.12023v1","created_at":"2026-07-05T01:45:32.899099+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12023","created_at":"2026-07-05T01:45:32.899099+00:00"},{"alias_kind":"pith_short_12","alias_value":"7CVWKOPRB7TV","created_at":"2026-07-05T01:45:32.899099+00:00"},{"alias_kind":"pith_short_16","alias_value":"7CVWKOPRB7TV4ZJ4","created_at":"2026-07-05T01:45:32.899099+00:00"},{"alias_kind":"pith_short_8","alias_value":"7CVWKOPR","created_at":"2026-07-05T01:45:32.899099+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.08339","citing_title":"SHeRL-FL: When Representation Learning Meets Split Learning in Hierarchical Federated Learning","ref_index":58,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7CVWKOPRB7TV4ZJ4LYI226U2IX","json":"https://pith.science/pith/7CVWKOPRB7TV4ZJ4LYI226U2IX.json","graph_json":"https://pith.science/api/pith-number/7CVWKOPRB7TV4ZJ4LYI226U2IX/graph.json","events_json":"https://pith.science/api/pith-number/7CVWKOPRB7TV4ZJ4LYI226U2IX/events.json","paper":"https://pith.science/paper/7CVWKOPR"},"agent_actions":{"view_html":"https://pith.science/pith/7CVWKOPRB7TV4ZJ4LYI226U2IX","download_json":"https://pith.science/pith/7CVWKOPRB7TV4ZJ4LYI226U2IX.json","view_paper":"https://pith.science/paper/7CVWKOPR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.12023&json=true","fetch_graph":"https://pith.science/api/pith-number/7CVWKOPRB7TV4ZJ4LYI226U2IX/graph.json","fetch_events":"https://pith.science/api/pith-number/7CVWKOPRB7TV4ZJ4LYI226U2IX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7CVWKOPRB7TV4ZJ4LYI226U2IX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7CVWKOPRB7TV4ZJ4LYI226U2IX/action/storage_attestation","attest_author":"https://pith.science/pith/7CVWKOPRB7TV4ZJ4LYI226U2IX/action/author_attestation","sign_citation":"https://pith.science/pith/7CVWKOPRB7TV4ZJ4LYI226U2IX/action/citation_signature","submit_replication":"https://pith.science/pith/7CVWKOPRB7TV4ZJ4LYI226U2IX/action/replication_record"}},"created_at":"2026-07-05T01:45:32.899099+00:00","updated_at":"2026-07-05T01:45:32.899099+00:00"}