{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SW2TOVI5YX6KGOJFHR7HBJRKO3","short_pith_number":"pith:SW2TOVI5","schema_version":"1.0","canonical_sha256":"95b537551dc5fca339253c7e70a62a76fabf61822d13f463d918f5a3c85e8ece","source":{"kind":"arxiv","id":"2304.10326","version":1},"attestation_state":"computed","paper":{"title":"Ensembling Instance and Semantic Segmentation for Panoptic Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mehmet Yildirim, Yogesh Langhe","submitted_at":"2023-04-20T14:02:01Z","abstract_excerpt":"We demonstrate our solution for the 2019 COCO panoptic segmentation task. Our method first performs instance segmentation and semantic segmentation separately, then combines the two to generate panoptic segmentation results. To enhance the performance, we add several expert models of Mask R-CNN in instance segmentation to tackle the data imbalance problem in the training data; also HTC model is adopted yielding our best instance segmentation results. In semantic segmentation, we trained several models with various backbones and use an ensemble strategy which further boosts the segmentation res"},"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":"2304.10326","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-20T14:02:01Z","cross_cats_sorted":[],"title_canon_sha256":"60c2292c0e3ab44f3c587b280bea29181dde73f8e16bc8164dccc9702c02eddd","abstract_canon_sha256":"0c9ca3634fe15f046760fee84e83c5c7f0eafd4ed8c58f172bb46cf58bedc34c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:02:56.995873Z","signature_b64":"y9hccz5o42/a4DtM6uIL/yq2wb9+S80SC3hO8hrvd3SG4+eD/jgSzrj1IJJJ9+uURCGcnybrj+EVzsa1nJYkAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95b537551dc5fca339253c7e70a62a76fabf61822d13f463d918f5a3c85e8ece","last_reissued_at":"2026-07-05T06:02:56.995483Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:02:56.995483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ensembling Instance and Semantic Segmentation for Panoptic Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mehmet Yildirim, Yogesh Langhe","submitted_at":"2023-04-20T14:02:01Z","abstract_excerpt":"We demonstrate our solution for the 2019 COCO panoptic segmentation task. Our method first performs instance segmentation and semantic segmentation separately, then combines the two to generate panoptic segmentation results. To enhance the performance, we add several expert models of Mask R-CNN in instance segmentation to tackle the data imbalance problem in the training data; also HTC model is adopted yielding our best instance segmentation results. In semantic segmentation, we trained several models with various backbones and use an ensemble strategy which further boosts the segmentation res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.10326","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/2304.10326/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":"2304.10326","created_at":"2026-07-05T06:02:56.995546+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.10326v1","created_at":"2026-07-05T06:02:56.995546+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.10326","created_at":"2026-07-05T06:02:56.995546+00:00"},{"alias_kind":"pith_short_12","alias_value":"SW2TOVI5YX6K","created_at":"2026-07-05T06:02:56.995546+00:00"},{"alias_kind":"pith_short_16","alias_value":"SW2TOVI5YX6KGOJF","created_at":"2026-07-05T06:02:56.995546+00:00"},{"alias_kind":"pith_short_8","alias_value":"SW2TOVI5","created_at":"2026-07-05T06:02:56.995546+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.16467","citing_title":"Cross-Domain Semantic Segmentation with Large Language Model-Assisted Descriptor Generation","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SW2TOVI5YX6KGOJFHR7HBJRKO3","json":"https://pith.science/pith/SW2TOVI5YX6KGOJFHR7HBJRKO3.json","graph_json":"https://pith.science/api/pith-number/SW2TOVI5YX6KGOJFHR7HBJRKO3/graph.json","events_json":"https://pith.science/api/pith-number/SW2TOVI5YX6KGOJFHR7HBJRKO3/events.json","paper":"https://pith.science/paper/SW2TOVI5"},"agent_actions":{"view_html":"https://pith.science/pith/SW2TOVI5YX6KGOJFHR7HBJRKO3","download_json":"https://pith.science/pith/SW2TOVI5YX6KGOJFHR7HBJRKO3.json","view_paper":"https://pith.science/paper/SW2TOVI5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.10326&json=true","fetch_graph":"https://pith.science/api/pith-number/SW2TOVI5YX6KGOJFHR7HBJRKO3/graph.json","fetch_events":"https://pith.science/api/pith-number/SW2TOVI5YX6KGOJFHR7HBJRKO3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SW2TOVI5YX6KGOJFHR7HBJRKO3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SW2TOVI5YX6KGOJFHR7HBJRKO3/action/storage_attestation","attest_author":"https://pith.science/pith/SW2TOVI5YX6KGOJFHR7HBJRKO3/action/author_attestation","sign_citation":"https://pith.science/pith/SW2TOVI5YX6KGOJFHR7HBJRKO3/action/citation_signature","submit_replication":"https://pith.science/pith/SW2TOVI5YX6KGOJFHR7HBJRKO3/action/replication_record"}},"created_at":"2026-07-05T06:02:56.995546+00:00","updated_at":"2026-07-05T06:02:56.995546+00:00"}