{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3AL6TLWN4RWKVLLZFTNGOEKT4Q","short_pith_number":"pith:3AL6TLWN","schema_version":"1.0","canonical_sha256":"d817e9aecde46caaad792cda671153e41f8554f802652a245ad678ba887059f2","source":{"kind":"arxiv","id":"2312.17492","version":2},"attestation_state":"computed","paper":{"title":"HEAP: Unsupervised Object Discovery and Localization with Contrastive Grouping","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinheng Xie, Michael Bi Mi, Robby T. Tan, Xin Zhang, Yuan Yuan","submitted_at":"2023-12-29T06:46:37Z","abstract_excerpt":"Unsupervised object discovery and localization aims to detect or segment objects in an image without any supervision. Recent efforts have demonstrated a notable potential to identify salient foreground objects by utilizing self-supervised transformer features. However, their scopes only build upon patch-level features within an image, neglecting region/image-level and cross-image relationships at a broader scale. Moreover, these methods cannot differentiate various semantics from multiple instances. To address these problems, we introduce Hierarchical mErging framework via contrAstive grouPing"},"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":"2312.17492","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-29T06:46:37Z","cross_cats_sorted":[],"title_canon_sha256":"964313c25985c4ad774fd33a6ea1e00ade983cf149c7130c7aaafcca64f0b83b","abstract_canon_sha256":"f3f54a5eac0e536b1b1a39856a93d3487be52bb39eccc4f901c5e662d07943d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:30:07.278387Z","signature_b64":"7wRLgm5ZggFBrpd1I5t5Buh9dvNUBbLTtZYerU5pahNoBf34mwbPFQAJy8kikrD6WgpYLAvizMqnl/2Pr4XQBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d817e9aecde46caaad792cda671153e41f8554f802652a245ad678ba887059f2","last_reissued_at":"2026-07-05T07:30:07.277794Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:30:07.277794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HEAP: Unsupervised Object Discovery and Localization with Contrastive Grouping","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinheng Xie, Michael Bi Mi, Robby T. Tan, Xin Zhang, Yuan Yuan","submitted_at":"2023-12-29T06:46:37Z","abstract_excerpt":"Unsupervised object discovery and localization aims to detect or segment objects in an image without any supervision. Recent efforts have demonstrated a notable potential to identify salient foreground objects by utilizing self-supervised transformer features. However, their scopes only build upon patch-level features within an image, neglecting region/image-level and cross-image relationships at a broader scale. Moreover, these methods cannot differentiate various semantics from multiple instances. To address these problems, we introduce Hierarchical mErging framework via contrAstive grouPing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.17492","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/2312.17492/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":"2312.17492","created_at":"2026-07-05T07:30:07.277866+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.17492v2","created_at":"2026-07-05T07:30:07.277866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.17492","created_at":"2026-07-05T07:30:07.277866+00:00"},{"alias_kind":"pith_short_12","alias_value":"3AL6TLWN4RWK","created_at":"2026-07-05T07:30:07.277866+00:00"},{"alias_kind":"pith_short_16","alias_value":"3AL6TLWN4RWKVLLZ","created_at":"2026-07-05T07:30:07.277866+00:00"},{"alias_kind":"pith_short_8","alias_value":"3AL6TLWN","created_at":"2026-07-05T07:30:07.277866+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00665","citing_title":"ER-LoRA: Effective-Rank Guided Adaptation for Weather-Generalized Depth Estimation","ref_index":80,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3AL6TLWN4RWKVLLZFTNGOEKT4Q","json":"https://pith.science/pith/3AL6TLWN4RWKVLLZFTNGOEKT4Q.json","graph_json":"https://pith.science/api/pith-number/3AL6TLWN4RWKVLLZFTNGOEKT4Q/graph.json","events_json":"https://pith.science/api/pith-number/3AL6TLWN4RWKVLLZFTNGOEKT4Q/events.json","paper":"https://pith.science/paper/3AL6TLWN"},"agent_actions":{"view_html":"https://pith.science/pith/3AL6TLWN4RWKVLLZFTNGOEKT4Q","download_json":"https://pith.science/pith/3AL6TLWN4RWKVLLZFTNGOEKT4Q.json","view_paper":"https://pith.science/paper/3AL6TLWN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.17492&json=true","fetch_graph":"https://pith.science/api/pith-number/3AL6TLWN4RWKVLLZFTNGOEKT4Q/graph.json","fetch_events":"https://pith.science/api/pith-number/3AL6TLWN4RWKVLLZFTNGOEKT4Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3AL6TLWN4RWKVLLZFTNGOEKT4Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3AL6TLWN4RWKVLLZFTNGOEKT4Q/action/storage_attestation","attest_author":"https://pith.science/pith/3AL6TLWN4RWKVLLZFTNGOEKT4Q/action/author_attestation","sign_citation":"https://pith.science/pith/3AL6TLWN4RWKVLLZFTNGOEKT4Q/action/citation_signature","submit_replication":"https://pith.science/pith/3AL6TLWN4RWKVLLZFTNGOEKT4Q/action/replication_record"}},"created_at":"2026-07-05T07:30:07.277866+00:00","updated_at":"2026-07-05T07:30:07.277866+00:00"}