{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:FLRQFB2ZT4IPNCBHU5EV5XMHRI","short_pith_number":"pith:FLRQFB2Z","schema_version":"1.0","canonical_sha256":"2ae30287599f10f68827a7495edd878a228b33277ad7fef1daf5fe6b7c495a48","source":{"kind":"arxiv","id":"1911.07160","version":5},"attestation_state":"computed","paper":{"title":"Improve CAM with Auto-adapted Segmentation and Co-supervised Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenliang Xu, Guofeng Cui, Shaojie Wang, Wentian Zhao, Ziyi Kou","submitted_at":"2019-11-17T06:12:36Z","abstract_excerpt":"Weakly Supervised Object Localization (WSOL) methods generate both classification and localization results by learning from only image category labels. Previous methods usually utilize class activation map (CAM) to obtain target object regions. However, most of them only focus on improving foreground object parts in CAM, but ignore the important effect of its background contents. In this paper, we propose a confidence segmentation (ConfSeg) module that builds confidence score for each pixel in CAM without introducing additional hyper-parameters. The generated sample-specific confidence mask is"},"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":"1911.07160","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-17T06:12:36Z","cross_cats_sorted":[],"title_canon_sha256":"2dceb744bbc7f6754f0c1b2074248eeb09111e7d043901ebb0f7f82f940556d2","abstract_canon_sha256":"c830f33ab74d3c5ec318f8cd618d7fb1f335c96f4a8a94f722d386206df78ee4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:06:29.017448Z","signature_b64":"7RkYVneVTWUfTNIej5sV66307amuG1DiSjC6ogofHPyNLWXB/FZXbtdL9pKAbLccdKQKesSeTDpMnu8lvE1oAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ae30287599f10f68827a7495edd878a228b33277ad7fef1daf5fe6b7c495a48","last_reissued_at":"2026-07-05T02:06:29.017096Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:06:29.017096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improve CAM with Auto-adapted Segmentation and Co-supervised Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenliang Xu, Guofeng Cui, Shaojie Wang, Wentian Zhao, Ziyi Kou","submitted_at":"2019-11-17T06:12:36Z","abstract_excerpt":"Weakly Supervised Object Localization (WSOL) methods generate both classification and localization results by learning from only image category labels. Previous methods usually utilize class activation map (CAM) to obtain target object regions. However, most of them only focus on improving foreground object parts in CAM, but ignore the important effect of its background contents. In this paper, we propose a confidence segmentation (ConfSeg) module that builds confidence score for each pixel in CAM without introducing additional hyper-parameters. The generated sample-specific confidence mask is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.07160","kind":"arxiv","version":5},"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/1911.07160/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":"1911.07160","created_at":"2026-07-05T02:06:29.017152+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.07160v5","created_at":"2026-07-05T02:06:29.017152+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.07160","created_at":"2026-07-05T02:06:29.017152+00:00"},{"alias_kind":"pith_short_12","alias_value":"FLRQFB2ZT4IP","created_at":"2026-07-05T02:06:29.017152+00:00"},{"alias_kind":"pith_short_16","alias_value":"FLRQFB2ZT4IPNCBH","created_at":"2026-07-05T02:06:29.017152+00:00"},{"alias_kind":"pith_short_8","alias_value":"FLRQFB2Z","created_at":"2026-07-05T02:06:29.017152+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/FLRQFB2ZT4IPNCBHU5EV5XMHRI","json":"https://pith.science/pith/FLRQFB2ZT4IPNCBHU5EV5XMHRI.json","graph_json":"https://pith.science/api/pith-number/FLRQFB2ZT4IPNCBHU5EV5XMHRI/graph.json","events_json":"https://pith.science/api/pith-number/FLRQFB2ZT4IPNCBHU5EV5XMHRI/events.json","paper":"https://pith.science/paper/FLRQFB2Z"},"agent_actions":{"view_html":"https://pith.science/pith/FLRQFB2ZT4IPNCBHU5EV5XMHRI","download_json":"https://pith.science/pith/FLRQFB2ZT4IPNCBHU5EV5XMHRI.json","view_paper":"https://pith.science/paper/FLRQFB2Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.07160&json=true","fetch_graph":"https://pith.science/api/pith-number/FLRQFB2ZT4IPNCBHU5EV5XMHRI/graph.json","fetch_events":"https://pith.science/api/pith-number/FLRQFB2ZT4IPNCBHU5EV5XMHRI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FLRQFB2ZT4IPNCBHU5EV5XMHRI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FLRQFB2ZT4IPNCBHU5EV5XMHRI/action/storage_attestation","attest_author":"https://pith.science/pith/FLRQFB2ZT4IPNCBHU5EV5XMHRI/action/author_attestation","sign_citation":"https://pith.science/pith/FLRQFB2ZT4IPNCBHU5EV5XMHRI/action/citation_signature","submit_replication":"https://pith.science/pith/FLRQFB2ZT4IPNCBHU5EV5XMHRI/action/replication_record"}},"created_at":"2026-07-05T02:06:29.017152+00:00","updated_at":"2026-07-05T02:06:29.017152+00:00"}