{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5X3NECKG3P35JZZLCCLMFIAPF3","short_pith_number":"pith:5X3NECKG","schema_version":"1.0","canonical_sha256":"edf6d20946dbf7d4e72b1096c2a00f2ee8ad55eaa89b2289ea8db5085f37d53e","source":{"kind":"arxiv","id":"2208.14439","version":1},"attestation_state":"computed","paper":{"title":"Self-Supervised Pyramid Representation Learning for Multi-Label Visual Analysis and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Cheng-Yen Hsieh, Chih-Jung Chang, Fu-En Yang, Yu-Chiang Frank Wang","submitted_at":"2022-08-30T17:57:14Z","abstract_excerpt":"While self-supervised learning has been shown to benefit a number of vision tasks, existing techniques mainly focus on image-level manipulation, which may not generalize well to downstream tasks at patch or pixel levels. Moreover, existing SSL methods might not sufficiently describe and associate the above representations within and across image scales. In this paper, we propose a Self-Supervised Pyramid Representation Learning (SS-PRL) framework. The proposed SS-PRL is designed to derive pyramid representations at patch levels via learning proper prototypes, with additional learners to observ"},"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":"2208.14439","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-30T17:57:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0d31ab12c12ed0f311ac2d56b4339d45b2cd37bf64a4576118e46235cb3de455","abstract_canon_sha256":"32b5f7b3bbac36e383247e2e1be61c8f0ae048ce0dec29786038af2d07c6607d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:53:12.182908Z","signature_b64":"5Eiw/VjCE0xkJHTNpXMxSQ3tezl928jXfMsiXvUtWrqDWoYmLV4FY4Xz/hwjrsPbhWM7zp+igIZoRfv9aLgsDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edf6d20946dbf7d4e72b1096c2a00f2ee8ad55eaa89b2289ea8db5085f37d53e","last_reissued_at":"2026-07-05T04:53:12.182384Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:53:12.182384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Supervised Pyramid Representation Learning for Multi-Label Visual Analysis and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Cheng-Yen Hsieh, Chih-Jung Chang, Fu-En Yang, Yu-Chiang Frank Wang","submitted_at":"2022-08-30T17:57:14Z","abstract_excerpt":"While self-supervised learning has been shown to benefit a number of vision tasks, existing techniques mainly focus on image-level manipulation, which may not generalize well to downstream tasks at patch or pixel levels. Moreover, existing SSL methods might not sufficiently describe and associate the above representations within and across image scales. In this paper, we propose a Self-Supervised Pyramid Representation Learning (SS-PRL) framework. The proposed SS-PRL is designed to derive pyramid representations at patch levels via learning proper prototypes, with additional learners to observ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.14439","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/2208.14439/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":"2208.14439","created_at":"2026-07-05T04:53:12.182443+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.14439v1","created_at":"2026-07-05T04:53:12.182443+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.14439","created_at":"2026-07-05T04:53:12.182443+00:00"},{"alias_kind":"pith_short_12","alias_value":"5X3NECKG3P35","created_at":"2026-07-05T04:53:12.182443+00:00"},{"alias_kind":"pith_short_16","alias_value":"5X3NECKG3P35JZZL","created_at":"2026-07-05T04:53:12.182443+00:00"},{"alias_kind":"pith_short_8","alias_value":"5X3NECKG","created_at":"2026-07-05T04:53:12.182443+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/5X3NECKG3P35JZZLCCLMFIAPF3","json":"https://pith.science/pith/5X3NECKG3P35JZZLCCLMFIAPF3.json","graph_json":"https://pith.science/api/pith-number/5X3NECKG3P35JZZLCCLMFIAPF3/graph.json","events_json":"https://pith.science/api/pith-number/5X3NECKG3P35JZZLCCLMFIAPF3/events.json","paper":"https://pith.science/paper/5X3NECKG"},"agent_actions":{"view_html":"https://pith.science/pith/5X3NECKG3P35JZZLCCLMFIAPF3","download_json":"https://pith.science/pith/5X3NECKG3P35JZZLCCLMFIAPF3.json","view_paper":"https://pith.science/paper/5X3NECKG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.14439&json=true","fetch_graph":"https://pith.science/api/pith-number/5X3NECKG3P35JZZLCCLMFIAPF3/graph.json","fetch_events":"https://pith.science/api/pith-number/5X3NECKG3P35JZZLCCLMFIAPF3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5X3NECKG3P35JZZLCCLMFIAPF3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5X3NECKG3P35JZZLCCLMFIAPF3/action/storage_attestation","attest_author":"https://pith.science/pith/5X3NECKG3P35JZZLCCLMFIAPF3/action/author_attestation","sign_citation":"https://pith.science/pith/5X3NECKG3P35JZZLCCLMFIAPF3/action/citation_signature","submit_replication":"https://pith.science/pith/5X3NECKG3P35JZZLCCLMFIAPF3/action/replication_record"}},"created_at":"2026-07-05T04:53:12.182443+00:00","updated_at":"2026-07-05T04:53:12.182443+00:00"}