{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4EUHLICB4QPBKON2GZCQY5IJPU","short_pith_number":"pith:4EUHLICB","schema_version":"1.0","canonical_sha256":"e12875a041e41e1539ba36450c75097d099e024a16cd5cc9ea2e5c08eb08b732","source":{"kind":"arxiv","id":"2211.11679","version":3},"attestation_state":"computed","paper":{"title":"Mean Shift Mask Transformer for Unseen Object Instance Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Nicholas Ruozzi, Yangxiao Lu, Yuqiao Chen, Yu Xiang","submitted_at":"2022-11-21T17:47:48Z","abstract_excerpt":"Segmenting unseen objects from images is a critical perception skill that a robot needs to acquire. In robot manipulation, it can facilitate a robot to grasp and manipulate unseen objects. Mean shift clustering is a widely used method for image segmentation tasks. However, the traditional mean shift clustering algorithm is not differentiable, making it difficult to integrate it into an end-to-end neural network training framework. In this work, we propose the Mean Shift Mask Transformer (MSMFormer), a new transformer architecture that simulates the von Mises-Fisher (vMF) mean shift clustering "},"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":"2211.11679","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-21T17:47:48Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"81213600a2ea3fdf41f72e984b1a9500c3da4f9b2233543c19d671dd9739be28","abstract_canon_sha256":"540c0ddd82f4be470dc51c0b96ed796ebc0e5060b0ad7c18c5abecfac063a71b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:53:04.186513Z","signature_b64":"i6fpTdmVqigwT5t+uCdz9nq3HE6oxHOALb59AOIDWCSIq18l2Y2gF0//GRhx4hAXSWyco2ZVW5sSDUG1QJHBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e12875a041e41e1539ba36450c75097d099e024a16cd5cc9ea2e5c08eb08b732","last_reissued_at":"2026-07-05T06:53:04.185996Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:53:04.185996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mean Shift Mask Transformer for Unseen Object Instance Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Nicholas Ruozzi, Yangxiao Lu, Yuqiao Chen, Yu Xiang","submitted_at":"2022-11-21T17:47:48Z","abstract_excerpt":"Segmenting unseen objects from images is a critical perception skill that a robot needs to acquire. In robot manipulation, it can facilitate a robot to grasp and manipulate unseen objects. Mean shift clustering is a widely used method for image segmentation tasks. However, the traditional mean shift clustering algorithm is not differentiable, making it difficult to integrate it into an end-to-end neural network training framework. In this work, we propose the Mean Shift Mask Transformer (MSMFormer), a new transformer architecture that simulates the von Mises-Fisher (vMF) mean shift clustering "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.11679","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/2211.11679/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":"2211.11679","created_at":"2026-07-05T06:53:04.186061+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.11679v3","created_at":"2026-07-05T06:53:04.186061+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.11679","created_at":"2026-07-05T06:53:04.186061+00:00"},{"alias_kind":"pith_short_12","alias_value":"4EUHLICB4QPB","created_at":"2026-07-05T06:53:04.186061+00:00"},{"alias_kind":"pith_short_16","alias_value":"4EUHLICB4QPBKON2","created_at":"2026-07-05T06:53:04.186061+00:00"},{"alias_kind":"pith_short_8","alias_value":"4EUHLICB","created_at":"2026-07-05T06:53:04.186061+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.03266","citing_title":"ZISVFM: Zero-Shot Object Instance Segmentation in Indoor Robotic Environments with Vision Foundation Models","ref_index":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4EUHLICB4QPBKON2GZCQY5IJPU","json":"https://pith.science/pith/4EUHLICB4QPBKON2GZCQY5IJPU.json","graph_json":"https://pith.science/api/pith-number/4EUHLICB4QPBKON2GZCQY5IJPU/graph.json","events_json":"https://pith.science/api/pith-number/4EUHLICB4QPBKON2GZCQY5IJPU/events.json","paper":"https://pith.science/paper/4EUHLICB"},"agent_actions":{"view_html":"https://pith.science/pith/4EUHLICB4QPBKON2GZCQY5IJPU","download_json":"https://pith.science/pith/4EUHLICB4QPBKON2GZCQY5IJPU.json","view_paper":"https://pith.science/paper/4EUHLICB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.11679&json=true","fetch_graph":"https://pith.science/api/pith-number/4EUHLICB4QPBKON2GZCQY5IJPU/graph.json","fetch_events":"https://pith.science/api/pith-number/4EUHLICB4QPBKON2GZCQY5IJPU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4EUHLICB4QPBKON2GZCQY5IJPU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4EUHLICB4QPBKON2GZCQY5IJPU/action/storage_attestation","attest_author":"https://pith.science/pith/4EUHLICB4QPBKON2GZCQY5IJPU/action/author_attestation","sign_citation":"https://pith.science/pith/4EUHLICB4QPBKON2GZCQY5IJPU/action/citation_signature","submit_replication":"https://pith.science/pith/4EUHLICB4QPBKON2GZCQY5IJPU/action/replication_record"}},"created_at":"2026-07-05T06:53:04.186061+00:00","updated_at":"2026-07-05T06:53:04.186061+00:00"}