{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:OJLEUJQ4PTDWSGIU66B3VUS2MM","short_pith_number":"pith:OJLEUJQ4","schema_version":"1.0","canonical_sha256":"72564a261c7cc7691914f783bad25a63257b839a7f9a1d68c54ffb9360971cf0","source":{"kind":"arxiv","id":"2109.01359","version":2},"attestation_state":"computed","paper":{"title":"CAM-loss: Towards Learning Spatially Discriminative Feature Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaofei Wang, Gao Huang, Jiayu Xiao, Qisen Yang, Shiji Song, Yizeng Han","submitted_at":"2021-09-03T08:04:17Z","abstract_excerpt":"The backbone of traditional CNN classifier is generally considered as a feature extractor, followed by a linear layer which performs the classification. We propose a novel loss function, termed as CAM-loss, to constrain the embedded feature maps with the class activation maps (CAMs) which indicate the spatially discriminative regions of an image for particular categories. CAM-loss drives the backbone to express the features of target category and suppress the features of non-target categories or background, so as to obtain more discriminative feature representations. It can be simply applied i"},"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":"2109.01359","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-03T08:04:17Z","cross_cats_sorted":[],"title_canon_sha256":"6680903b87bfc20053a0d4f208187729ef99ae858309811efc7b604a63da9860","abstract_canon_sha256":"4b37c7eb855a92686302e1cfbf21eb6a0fa97c8a20f7912e7f588cf6a6055da0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:02:56.092771Z","signature_b64":"VJZBeqYb9lqJ/C8onXiKkJrZSpmq9uon7RNhRbfm7LpccpV3XifN3igrbBCexH6mYbsrKBjE/fLlcwjn8hTcDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72564a261c7cc7691914f783bad25a63257b839a7f9a1d68c54ffb9360971cf0","last_reissued_at":"2026-07-05T04:02:56.092322Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:02:56.092322Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CAM-loss: Towards Learning Spatially Discriminative Feature Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaofei Wang, Gao Huang, Jiayu Xiao, Qisen Yang, Shiji Song, Yizeng Han","submitted_at":"2021-09-03T08:04:17Z","abstract_excerpt":"The backbone of traditional CNN classifier is generally considered as a feature extractor, followed by a linear layer which performs the classification. We propose a novel loss function, termed as CAM-loss, to constrain the embedded feature maps with the class activation maps (CAMs) which indicate the spatially discriminative regions of an image for particular categories. CAM-loss drives the backbone to express the features of target category and suppress the features of non-target categories or background, so as to obtain more discriminative feature representations. It can be simply applied i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.01359","kind":"arxiv","version":2},"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/2109.01359/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":"2109.01359","created_at":"2026-07-05T04:02:56.092373+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.01359v2","created_at":"2026-07-05T04:02:56.092373+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.01359","created_at":"2026-07-05T04:02:56.092373+00:00"},{"alias_kind":"pith_short_12","alias_value":"OJLEUJQ4PTDW","created_at":"2026-07-05T04:02:56.092373+00:00"},{"alias_kind":"pith_short_16","alias_value":"OJLEUJQ4PTDWSGIU","created_at":"2026-07-05T04:02:56.092373+00:00"},{"alias_kind":"pith_short_8","alias_value":"OJLEUJQ4","created_at":"2026-07-05T04:02:56.092373+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/OJLEUJQ4PTDWSGIU66B3VUS2MM","json":"https://pith.science/pith/OJLEUJQ4PTDWSGIU66B3VUS2MM.json","graph_json":"https://pith.science/api/pith-number/OJLEUJQ4PTDWSGIU66B3VUS2MM/graph.json","events_json":"https://pith.science/api/pith-number/OJLEUJQ4PTDWSGIU66B3VUS2MM/events.json","paper":"https://pith.science/paper/OJLEUJQ4"},"agent_actions":{"view_html":"https://pith.science/pith/OJLEUJQ4PTDWSGIU66B3VUS2MM","download_json":"https://pith.science/pith/OJLEUJQ4PTDWSGIU66B3VUS2MM.json","view_paper":"https://pith.science/paper/OJLEUJQ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.01359&json=true","fetch_graph":"https://pith.science/api/pith-number/OJLEUJQ4PTDWSGIU66B3VUS2MM/graph.json","fetch_events":"https://pith.science/api/pith-number/OJLEUJQ4PTDWSGIU66B3VUS2MM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OJLEUJQ4PTDWSGIU66B3VUS2MM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OJLEUJQ4PTDWSGIU66B3VUS2MM/action/storage_attestation","attest_author":"https://pith.science/pith/OJLEUJQ4PTDWSGIU66B3VUS2MM/action/author_attestation","sign_citation":"https://pith.science/pith/OJLEUJQ4PTDWSGIU66B3VUS2MM/action/citation_signature","submit_replication":"https://pith.science/pith/OJLEUJQ4PTDWSGIU66B3VUS2MM/action/replication_record"}},"created_at":"2026-07-05T04:02:56.092373+00:00","updated_at":"2026-07-05T04:02:56.092373+00:00"}