{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:TBZW5N3KILTVOTLW34FG5IMFML","short_pith_number":"pith:TBZW5N3K","schema_version":"1.0","canonical_sha256":"98736eb76a42e7574d76df0a6ea18562dd59ef5b65b7dd0e2cea6a61a3c75732","source":{"kind":"arxiv","id":"2107.00583","version":3},"attestation_state":"computed","paper":{"title":"Inter Extreme Points Geodesics for End-to-End Weakly Supervised Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aaron Kujawa, Jonathan Shapey, Marc Modat, Reuben Dorent, Samuel Joutard, Sebastien Ourselin, Tom Vercauteren","submitted_at":"2021-07-01T16:16:50Z","abstract_excerpt":"We introduce $\\textit{InExtremIS}$, a weakly supervised 3D approach to train a deep image segmentation network using particularly weak train-time annotations: only 6 extreme clicks at the boundary of the objects of interest. Our fully-automatic method is trained end-to-end and does not require any test-time annotations. From the extreme points, 3D bounding boxes are extracted around objects of interest. Then, deep geodesics connecting extreme points are generated to increase the amount of \"annotated\" voxels within the bounding boxes. Finally, a weakly supervised regularised loss derived from a"},"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":"2107.00583","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-01T16:16:50Z","cross_cats_sorted":[],"title_canon_sha256":"7e2e0fc992160a96127f4aafb0c464f47c0f422151d2ef6aabecad52e0ea85a6","abstract_canon_sha256":"77ed08dcfb16d1f3035cc790225f94c3e11a7d9e7c8d0b924099a95f9d52a9c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:29:17.609983Z","signature_b64":"lYdOiwLvZiIGYhlXrNl8keMDqqfUgmyG+R8/6ZBe5H6Dy78LEytDfSyq2JLKBF/cPFbPvC0ubGwMNP4irNVvCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98736eb76a42e7574d76df0a6ea18562dd59ef5b65b7dd0e2cea6a61a3c75732","last_reissued_at":"2026-07-05T03:29:17.609508Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:29:17.609508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inter Extreme Points Geodesics for End-to-End Weakly Supervised Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aaron Kujawa, Jonathan Shapey, Marc Modat, Reuben Dorent, Samuel Joutard, Sebastien Ourselin, Tom Vercauteren","submitted_at":"2021-07-01T16:16:50Z","abstract_excerpt":"We introduce $\\textit{InExtremIS}$, a weakly supervised 3D approach to train a deep image segmentation network using particularly weak train-time annotations: only 6 extreme clicks at the boundary of the objects of interest. Our fully-automatic method is trained end-to-end and does not require any test-time annotations. From the extreme points, 3D bounding boxes are extracted around objects of interest. Then, deep geodesics connecting extreme points are generated to increase the amount of \"annotated\" voxels within the bounding boxes. Finally, a weakly supervised regularised loss derived from a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.00583","kind":"arxiv","version":3},"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/2107.00583/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":"2107.00583","created_at":"2026-07-05T03:29:17.609569+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.00583v3","created_at":"2026-07-05T03:29:17.609569+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.00583","created_at":"2026-07-05T03:29:17.609569+00:00"},{"alias_kind":"pith_short_12","alias_value":"TBZW5N3KILTV","created_at":"2026-07-05T03:29:17.609569+00:00"},{"alias_kind":"pith_short_16","alias_value":"TBZW5N3KILTVOTLW","created_at":"2026-07-05T03:29:17.609569+00:00"},{"alias_kind":"pith_short_8","alias_value":"TBZW5N3K","created_at":"2026-07-05T03:29:17.609569+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/TBZW5N3KILTVOTLW34FG5IMFML","json":"https://pith.science/pith/TBZW5N3KILTVOTLW34FG5IMFML.json","graph_json":"https://pith.science/api/pith-number/TBZW5N3KILTVOTLW34FG5IMFML/graph.json","events_json":"https://pith.science/api/pith-number/TBZW5N3KILTVOTLW34FG5IMFML/events.json","paper":"https://pith.science/paper/TBZW5N3K"},"agent_actions":{"view_html":"https://pith.science/pith/TBZW5N3KILTVOTLW34FG5IMFML","download_json":"https://pith.science/pith/TBZW5N3KILTVOTLW34FG5IMFML.json","view_paper":"https://pith.science/paper/TBZW5N3K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.00583&json=true","fetch_graph":"https://pith.science/api/pith-number/TBZW5N3KILTVOTLW34FG5IMFML/graph.json","fetch_events":"https://pith.science/api/pith-number/TBZW5N3KILTVOTLW34FG5IMFML/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TBZW5N3KILTVOTLW34FG5IMFML/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TBZW5N3KILTVOTLW34FG5IMFML/action/storage_attestation","attest_author":"https://pith.science/pith/TBZW5N3KILTVOTLW34FG5IMFML/action/author_attestation","sign_citation":"https://pith.science/pith/TBZW5N3KILTVOTLW34FG5IMFML/action/citation_signature","submit_replication":"https://pith.science/pith/TBZW5N3KILTVOTLW34FG5IMFML/action/replication_record"}},"created_at":"2026-07-05T03:29:17.609569+00:00","updated_at":"2026-07-05T03:29:17.609569+00:00"}