{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4M5SZRV2YBTWIYJHHTES64UQHQ","short_pith_number":"pith:4M5SZRV2","schema_version":"1.0","canonical_sha256":"e33b2cc6bac0676461273cc92f72903c133bba2bca551efa6d8d108a0d83cf9b","source":{"kind":"arxiv","id":"2409.13687","version":1},"attestation_state":"computed","paper":{"title":"A Bottom-Up Approach to Class-Agnostic Image Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ari Blondal, Sebastian Dille, Sylvain Paris, Ya\\u{g}{\\i}z Aksoy","submitted_at":"2024-09-20T17:56:02Z","abstract_excerpt":"Class-agnostic image segmentation is a crucial component in automating image editing workflows, especially in contexts where object selection traditionally involves interactive tools. Existing methods in the literature often adhere to top-down formulations, following the paradigm of class-based approaches, where object detection precedes per-object segmentation. In this work, we present a novel bottom-up formulation for addressing the class-agnostic segmentation problem. We supervise our network directly on the projective sphere of its feature space, employing losses inspired by metric learnin"},"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":"2409.13687","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-20T17:56:02Z","cross_cats_sorted":[],"title_canon_sha256":"e3f09973031b8929b3510d5d01b3aee31ac23332c074d7b59c2e7b212a330788","abstract_canon_sha256":"f267023fad75da3a1ab4177dcdc149e811a4ba1c42c03ea5942d022270ac23dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:47.301781Z","signature_b64":"hoXNsrDx1sOrrg6Z4wONMuCBdfOyd+k5ImGLvAscy+UbtVJbPKCsjJBlL4y6Z7rMBKyJzltyn9mqyjdVPtupDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e33b2cc6bac0676461273cc92f72903c133bba2bca551efa6d8d108a0d83cf9b","last_reissued_at":"2026-07-05T09:09:47.301228Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:47.301228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Bottom-Up Approach to Class-Agnostic Image Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ari Blondal, Sebastian Dille, Sylvain Paris, Ya\\u{g}{\\i}z Aksoy","submitted_at":"2024-09-20T17:56:02Z","abstract_excerpt":"Class-agnostic image segmentation is a crucial component in automating image editing workflows, especially in contexts where object selection traditionally involves interactive tools. Existing methods in the literature often adhere to top-down formulations, following the paradigm of class-based approaches, where object detection precedes per-object segmentation. In this work, we present a novel bottom-up formulation for addressing the class-agnostic segmentation problem. We supervise our network directly on the projective sphere of its feature space, employing losses inspired by metric learnin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13687","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/2409.13687/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":"2409.13687","created_at":"2026-07-05T09:09:47.301296+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.13687v1","created_at":"2026-07-05T09:09:47.301296+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13687","created_at":"2026-07-05T09:09:47.301296+00:00"},{"alias_kind":"pith_short_12","alias_value":"4M5SZRV2YBTW","created_at":"2026-07-05T09:09:47.301296+00:00"},{"alias_kind":"pith_short_16","alias_value":"4M5SZRV2YBTWIYJH","created_at":"2026-07-05T09:09:47.301296+00:00"},{"alias_kind":"pith_short_8","alias_value":"4M5SZRV2","created_at":"2026-07-05T09:09:47.301296+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/4M5SZRV2YBTWIYJHHTES64UQHQ","json":"https://pith.science/pith/4M5SZRV2YBTWIYJHHTES64UQHQ.json","graph_json":"https://pith.science/api/pith-number/4M5SZRV2YBTWIYJHHTES64UQHQ/graph.json","events_json":"https://pith.science/api/pith-number/4M5SZRV2YBTWIYJHHTES64UQHQ/events.json","paper":"https://pith.science/paper/4M5SZRV2"},"agent_actions":{"view_html":"https://pith.science/pith/4M5SZRV2YBTWIYJHHTES64UQHQ","download_json":"https://pith.science/pith/4M5SZRV2YBTWIYJHHTES64UQHQ.json","view_paper":"https://pith.science/paper/4M5SZRV2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.13687&json=true","fetch_graph":"https://pith.science/api/pith-number/4M5SZRV2YBTWIYJHHTES64UQHQ/graph.json","fetch_events":"https://pith.science/api/pith-number/4M5SZRV2YBTWIYJHHTES64UQHQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4M5SZRV2YBTWIYJHHTES64UQHQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4M5SZRV2YBTWIYJHHTES64UQHQ/action/storage_attestation","attest_author":"https://pith.science/pith/4M5SZRV2YBTWIYJHHTES64UQHQ/action/author_attestation","sign_citation":"https://pith.science/pith/4M5SZRV2YBTWIYJHHTES64UQHQ/action/citation_signature","submit_replication":"https://pith.science/pith/4M5SZRV2YBTWIYJHHTES64UQHQ/action/replication_record"}},"created_at":"2026-07-05T09:09:47.301296+00:00","updated_at":"2026-07-05T09:09:47.301296+00:00"}