{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2RGYKDLYK4RTQ6R3FUBDVKUJDK","short_pith_number":"pith:2RGYKDLY","schema_version":"1.0","canonical_sha256":"d44d850d785723387a3b2d023aaa891aaa2a203590aa40d85553e654f088e7c2","source":{"kind":"arxiv","id":"2309.01692","version":1},"attestation_state":"computed","paper":{"title":"Mask-Attention-Free Transformer for 3D Instance Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Hu, Jiaya Jia, Ruihang Chu, Xin Lai, Yuhui Yuan, Yukang Chen","submitted_at":"2023-09-04T16:09:28Z","abstract_excerpt":"Recently, transformer-based methods have dominated 3D instance segmentation, where mask attention is commonly involved. Specifically, object queries are guided by the initial instance masks in the first cross-attention, and then iteratively refine themselves in a similar manner. However, we observe that the mask-attention pipeline usually leads to slow convergence due to low-recall initial instance masks. Therefore, we abandon the mask attention design and resort to an auxiliary center regression task instead. Through center regression, we effectively overcome the low-recall issue and perform "},"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":"2309.01692","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-04T16:09:28Z","cross_cats_sorted":[],"title_canon_sha256":"0fa786488e309a8f78a2c22f0ae3104fc28c9613b76a08bfc63af4f55ef77858","abstract_canon_sha256":"bad66cc21e93e797ae66c3baae736e9c39458ec9198e7fb17029c8e1bd366820"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:47:41.803196Z","signature_b64":"V6KPhWcvc0vb3sywpzGrGhgTe5RiS/hf0SRfrV3BlajGIMrXx7ZTOWC5oF9TPk6pyNniWTeofTqARiudmMcjAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d44d850d785723387a3b2d023aaa891aaa2a203590aa40d85553e654f088e7c2","last_reissued_at":"2026-07-05T06:47:41.802682Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:47:41.802682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mask-Attention-Free Transformer for 3D Instance Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Hu, Jiaya Jia, Ruihang Chu, Xin Lai, Yuhui Yuan, Yukang Chen","submitted_at":"2023-09-04T16:09:28Z","abstract_excerpt":"Recently, transformer-based methods have dominated 3D instance segmentation, where mask attention is commonly involved. Specifically, object queries are guided by the initial instance masks in the first cross-attention, and then iteratively refine themselves in a similar manner. However, we observe that the mask-attention pipeline usually leads to slow convergence due to low-recall initial instance masks. Therefore, we abandon the mask attention design and resort to an auxiliary center regression task instead. Through center regression, we effectively overcome the low-recall issue and perform "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.01692","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/2309.01692/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":"2309.01692","created_at":"2026-07-05T06:47:41.802751+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.01692v1","created_at":"2026-07-05T06:47:41.802751+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.01692","created_at":"2026-07-05T06:47:41.802751+00:00"},{"alias_kind":"pith_short_12","alias_value":"2RGYKDLYK4RT","created_at":"2026-07-05T06:47:41.802751+00:00"},{"alias_kind":"pith_short_16","alias_value":"2RGYKDLYK4RTQ6R3","created_at":"2026-07-05T06:47:41.802751+00:00"},{"alias_kind":"pith_short_8","alias_value":"2RGYKDLY","created_at":"2026-07-05T06:47:41.802751+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/2RGYKDLYK4RTQ6R3FUBDVKUJDK","json":"https://pith.science/pith/2RGYKDLYK4RTQ6R3FUBDVKUJDK.json","graph_json":"https://pith.science/api/pith-number/2RGYKDLYK4RTQ6R3FUBDVKUJDK/graph.json","events_json":"https://pith.science/api/pith-number/2RGYKDLYK4RTQ6R3FUBDVKUJDK/events.json","paper":"https://pith.science/paper/2RGYKDLY"},"agent_actions":{"view_html":"https://pith.science/pith/2RGYKDLYK4RTQ6R3FUBDVKUJDK","download_json":"https://pith.science/pith/2RGYKDLYK4RTQ6R3FUBDVKUJDK.json","view_paper":"https://pith.science/paper/2RGYKDLY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.01692&json=true","fetch_graph":"https://pith.science/api/pith-number/2RGYKDLYK4RTQ6R3FUBDVKUJDK/graph.json","fetch_events":"https://pith.science/api/pith-number/2RGYKDLYK4RTQ6R3FUBDVKUJDK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2RGYKDLYK4RTQ6R3FUBDVKUJDK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2RGYKDLYK4RTQ6R3FUBDVKUJDK/action/storage_attestation","attest_author":"https://pith.science/pith/2RGYKDLYK4RTQ6R3FUBDVKUJDK/action/author_attestation","sign_citation":"https://pith.science/pith/2RGYKDLYK4RTQ6R3FUBDVKUJDK/action/citation_signature","submit_replication":"https://pith.science/pith/2RGYKDLYK4RTQ6R3FUBDVKUJDK/action/replication_record"}},"created_at":"2026-07-05T06:47:41.802751+00:00","updated_at":"2026-07-05T06:47:41.802751+00:00"}