{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:7AZKCUHEBYDOBJX4K6AN6AEVXZ","short_pith_number":"pith:7AZKCUHE","schema_version":"1.0","canonical_sha256":"f832a150e40e06e0a6fc5780df0095be4ae1fc793139bc356e8a82d23d5bdc64","source":{"kind":"arxiv","id":"2111.13280","version":2},"attestation_state":"computed","paper":{"title":"Efficient Self-Ensemble for Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Archana Machireddy, Guillaume Thibault, Joe Gray, Lucas Pagano, Walid Bousselham, Xubo Song, Young Hwan Chang","submitted_at":"2021-11-26T00:35:09Z","abstract_excerpt":"Ensemble of predictions is known to perform better than individual predictions taken separately. However, for tasks that require heavy computational resources, e.g. semantic segmentation, creating an ensemble of learners that needs to be trained separately is hardly tractable. In this work, we propose to leverage the performance boost offered by ensemble methods to enhance the semantic segmentation, while avoiding the traditional heavy training cost of the ensemble. Our self-ensemble approach takes advantage of the multi-scale features set produced by feature pyramid network methods to feed in"},"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":"2111.13280","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-26T00:35:09Z","cross_cats_sorted":[],"title_canon_sha256":"60a3a464381266b519bfd5a1025513395358d418494157798e336d8f52203a98","abstract_canon_sha256":"898557cc33ab7217d4b117d085f0141204a9b36f80a8d466052d84a8a0144bd3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:07:06.625422Z","signature_b64":"AHFYwOFPPbj70hXeMFCCf7/MglpUcYeBJKP5/rpsdq3ENQJlqakRy3uXOgtcCVuKj8L5MnsKdxhoZxsqppHAAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f832a150e40e06e0a6fc5780df0095be4ae1fc793139bc356e8a82d23d5bdc64","last_reissued_at":"2026-07-05T04:07:06.624969Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:07:06.624969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Self-Ensemble for Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Archana Machireddy, Guillaume Thibault, Joe Gray, Lucas Pagano, Walid Bousselham, Xubo Song, Young Hwan Chang","submitted_at":"2021-11-26T00:35:09Z","abstract_excerpt":"Ensemble of predictions is known to perform better than individual predictions taken separately. However, for tasks that require heavy computational resources, e.g. semantic segmentation, creating an ensemble of learners that needs to be trained separately is hardly tractable. In this work, we propose to leverage the performance boost offered by ensemble methods to enhance the semantic segmentation, while avoiding the traditional heavy training cost of the ensemble. Our self-ensemble approach takes advantage of the multi-scale features set produced by feature pyramid network methods to feed in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.13280","kind":"arxiv","version":2},"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/2111.13280/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":"2111.13280","created_at":"2026-07-05T04:07:06.625033+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.13280v2","created_at":"2026-07-05T04:07:06.625033+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.13280","created_at":"2026-07-05T04:07:06.625033+00:00"},{"alias_kind":"pith_short_12","alias_value":"7AZKCUHEBYDO","created_at":"2026-07-05T04:07:06.625033+00:00"},{"alias_kind":"pith_short_16","alias_value":"7AZKCUHEBYDOBJX4","created_at":"2026-07-05T04:07:06.625033+00:00"},{"alias_kind":"pith_short_8","alias_value":"7AZKCUHE","created_at":"2026-07-05T04:07:06.625033+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23098","citing_title":"UfM*: Uncertainty from Motion* for DNN Depth Estimation Using Gaussians","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7AZKCUHEBYDOBJX4K6AN6AEVXZ","json":"https://pith.science/pith/7AZKCUHEBYDOBJX4K6AN6AEVXZ.json","graph_json":"https://pith.science/api/pith-number/7AZKCUHEBYDOBJX4K6AN6AEVXZ/graph.json","events_json":"https://pith.science/api/pith-number/7AZKCUHEBYDOBJX4K6AN6AEVXZ/events.json","paper":"https://pith.science/paper/7AZKCUHE"},"agent_actions":{"view_html":"https://pith.science/pith/7AZKCUHEBYDOBJX4K6AN6AEVXZ","download_json":"https://pith.science/pith/7AZKCUHEBYDOBJX4K6AN6AEVXZ.json","view_paper":"https://pith.science/paper/7AZKCUHE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.13280&json=true","fetch_graph":"https://pith.science/api/pith-number/7AZKCUHEBYDOBJX4K6AN6AEVXZ/graph.json","fetch_events":"https://pith.science/api/pith-number/7AZKCUHEBYDOBJX4K6AN6AEVXZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7AZKCUHEBYDOBJX4K6AN6AEVXZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7AZKCUHEBYDOBJX4K6AN6AEVXZ/action/storage_attestation","attest_author":"https://pith.science/pith/7AZKCUHEBYDOBJX4K6AN6AEVXZ/action/author_attestation","sign_citation":"https://pith.science/pith/7AZKCUHEBYDOBJX4K6AN6AEVXZ/action/citation_signature","submit_replication":"https://pith.science/pith/7AZKCUHEBYDOBJX4K6AN6AEVXZ/action/replication_record"}},"created_at":"2026-07-05T04:07:06.625033+00:00","updated_at":"2026-07-05T04:07:06.625033+00:00"}