{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RBOGZGQ7NE5FQ2SOM4N5JIOH2Y","short_pith_number":"pith:RBOGZGQ7","schema_version":"1.0","canonical_sha256":"885c6c9a1f693a586a4e671bd4a1c7d6292c7b6acd55070fd8755dcd125e639f","source":{"kind":"arxiv","id":"2208.11821","version":2},"attestation_state":"computed","paper":{"title":"Refine and Represent: Region-to-Object Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Akash Gokul, Colorado J Reed, Kazuki Kozuka, Konstantinos Kallidromitis, Shufan Li, Trevor Darrell, Yusuke Kato","submitted_at":"2022-08-25T01:44:28Z","abstract_excerpt":"Recent works in self-supervised learning have demonstrated strong performance on scene-level dense prediction tasks by pretraining with object-centric or region-based correspondence objectives. In this paper, we present Region-to-Object Representation Learning (R2O) which unifies region-based and object-centric pretraining. R2O operates by training an encoder to dynamically refine region-based segments into object-centric masks and then jointly learns representations of the contents within the mask. R2O uses a \"region refinement module\" to group small image regions, generated using a region-le"},"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":"2208.11821","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-08-25T01:44:28Z","cross_cats_sorted":[],"title_canon_sha256":"9e14b3eb546ad18c2da3191bc9bfd051671104bd8a0b2ad4fd831023b63e5218","abstract_canon_sha256":"936639eb25b78ab1d285efec358abe1536779aede62d8065d3bda4dffecb4f82"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:27:18.842248Z","signature_b64":"3ffmDB20Wo0jOt8uRc3jRTNas2HS0Wvtz5ISxIePap7Ue8Ak7bp9X4puZd08Dd2GZ8MRdQw9wiIUSbeesCNBAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"885c6c9a1f693a586a4e671bd4a1c7d6292c7b6acd55070fd8755dcd125e639f","last_reissued_at":"2026-07-05T05:27:18.841766Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:27:18.841766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Refine and Represent: Region-to-Object Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Akash Gokul, Colorado J Reed, Kazuki Kozuka, Konstantinos Kallidromitis, Shufan Li, Trevor Darrell, Yusuke Kato","submitted_at":"2022-08-25T01:44:28Z","abstract_excerpt":"Recent works in self-supervised learning have demonstrated strong performance on scene-level dense prediction tasks by pretraining with object-centric or region-based correspondence objectives. In this paper, we present Region-to-Object Representation Learning (R2O) which unifies region-based and object-centric pretraining. R2O operates by training an encoder to dynamically refine region-based segments into object-centric masks and then jointly learns representations of the contents within the mask. R2O uses a \"region refinement module\" to group small image regions, generated using a region-le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.11821","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/2208.11821/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":"2208.11821","created_at":"2026-07-05T05:27:18.841826+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.11821v2","created_at":"2026-07-05T05:27:18.841826+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.11821","created_at":"2026-07-05T05:27:18.841826+00:00"},{"alias_kind":"pith_short_12","alias_value":"RBOGZGQ7NE5F","created_at":"2026-07-05T05:27:18.841826+00:00"},{"alias_kind":"pith_short_16","alias_value":"RBOGZGQ7NE5FQ2SO","created_at":"2026-07-05T05:27:18.841826+00:00"},{"alias_kind":"pith_short_8","alias_value":"RBOGZGQ7","created_at":"2026-07-05T05:27:18.841826+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25402","citing_title":"Anatomy-Anchored Self-Supervision: Distilling Vision Foundation Models for Invariant Ultrasound Representation","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RBOGZGQ7NE5FQ2SOM4N5JIOH2Y","json":"https://pith.science/pith/RBOGZGQ7NE5FQ2SOM4N5JIOH2Y.json","graph_json":"https://pith.science/api/pith-number/RBOGZGQ7NE5FQ2SOM4N5JIOH2Y/graph.json","events_json":"https://pith.science/api/pith-number/RBOGZGQ7NE5FQ2SOM4N5JIOH2Y/events.json","paper":"https://pith.science/paper/RBOGZGQ7"},"agent_actions":{"view_html":"https://pith.science/pith/RBOGZGQ7NE5FQ2SOM4N5JIOH2Y","download_json":"https://pith.science/pith/RBOGZGQ7NE5FQ2SOM4N5JIOH2Y.json","view_paper":"https://pith.science/paper/RBOGZGQ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.11821&json=true","fetch_graph":"https://pith.science/api/pith-number/RBOGZGQ7NE5FQ2SOM4N5JIOH2Y/graph.json","fetch_events":"https://pith.science/api/pith-number/RBOGZGQ7NE5FQ2SOM4N5JIOH2Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RBOGZGQ7NE5FQ2SOM4N5JIOH2Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RBOGZGQ7NE5FQ2SOM4N5JIOH2Y/action/storage_attestation","attest_author":"https://pith.science/pith/RBOGZGQ7NE5FQ2SOM4N5JIOH2Y/action/author_attestation","sign_citation":"https://pith.science/pith/RBOGZGQ7NE5FQ2SOM4N5JIOH2Y/action/citation_signature","submit_replication":"https://pith.science/pith/RBOGZGQ7NE5FQ2SOM4N5JIOH2Y/action/replication_record"}},"created_at":"2026-07-05T05:27:18.841826+00:00","updated_at":"2026-07-05T05:27:18.841826+00:00"}