{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:HOCSZV4KJQKKPDRS3FKLWDQOCV","short_pith_number":"pith:HOCSZV4K","schema_version":"1.0","canonical_sha256":"3b852cd78a4c14a78e32d954bb0e0e15661692f690733f00b822e9dbc1b047ab","source":{"kind":"arxiv","id":"2011.11390","version":3},"attestation_state":"computed","paper":{"title":"PLOP: Learning without Forgetting for Continual Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arnaud Dapogny, Arthur Douillard, Matthieu Cord, Yifu Chen","submitted_at":"2020-11-23T13:35:03Z","abstract_excerpt":"Deep learning approaches are nowadays ubiquitously used to tackle computer vision tasks such as semantic segmentation, requiring large datasets and substantial computational power. Continual learning for semantic segmentation (CSS) is an emerging trend that consists in updating an old model by sequentially adding new classes. However, continual learning methods are usually prone to catastrophic forgetting. This issue is further aggravated in CSS where, at each step, old classes from previous iterations are collapsed into the background. In this paper, we propose Local POD, a multi-scale poolin"},"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":"2011.11390","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-11-23T13:35:03Z","cross_cats_sorted":[],"title_canon_sha256":"7e1887602f7a6d76228c8d38a1402ce413d4edcd702e671fcac7a9fc295dddf0","abstract_canon_sha256":"67dc22097f91ca4dbc44fc4fa8fd5d6b84a97ebad56187b649ae9fa72bb80559"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:22:06.581480Z","signature_b64":"J1LIdDDVnu/bYX/ZicC2uHfl6JhS3rzjx5H/4m1nE6YRaYuudoXMqj48JldttyyFC7Bbkeoof2aWIKy6j2G6Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b852cd78a4c14a78e32d954bb0e0e15661692f690733f00b822e9dbc1b047ab","last_reissued_at":"2026-07-05T02:22:06.581037Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:22:06.581037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PLOP: Learning without Forgetting for Continual Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arnaud Dapogny, Arthur Douillard, Matthieu Cord, Yifu Chen","submitted_at":"2020-11-23T13:35:03Z","abstract_excerpt":"Deep learning approaches are nowadays ubiquitously used to tackle computer vision tasks such as semantic segmentation, requiring large datasets and substantial computational power. Continual learning for semantic segmentation (CSS) is an emerging trend that consists in updating an old model by sequentially adding new classes. However, continual learning methods are usually prone to catastrophic forgetting. This issue is further aggravated in CSS where, at each step, old classes from previous iterations are collapsed into the background. In this paper, we propose Local POD, a multi-scale poolin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.11390","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/2011.11390/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":"2011.11390","created_at":"2026-07-05T02:22:06.581090+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.11390v3","created_at":"2026-07-05T02:22:06.581090+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.11390","created_at":"2026-07-05T02:22:06.581090+00:00"},{"alias_kind":"pith_short_12","alias_value":"HOCSZV4KJQKK","created_at":"2026-07-05T02:22:06.581090+00:00"},{"alias_kind":"pith_short_16","alias_value":"HOCSZV4KJQKKPDRS","created_at":"2026-07-05T02:22:06.581090+00:00"},{"alias_kind":"pith_short_8","alias_value":"HOCSZV4K","created_at":"2026-07-05T02:22:06.581090+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/HOCSZV4KJQKKPDRS3FKLWDQOCV","json":"https://pith.science/pith/HOCSZV4KJQKKPDRS3FKLWDQOCV.json","graph_json":"https://pith.science/api/pith-number/HOCSZV4KJQKKPDRS3FKLWDQOCV/graph.json","events_json":"https://pith.science/api/pith-number/HOCSZV4KJQKKPDRS3FKLWDQOCV/events.json","paper":"https://pith.science/paper/HOCSZV4K"},"agent_actions":{"view_html":"https://pith.science/pith/HOCSZV4KJQKKPDRS3FKLWDQOCV","download_json":"https://pith.science/pith/HOCSZV4KJQKKPDRS3FKLWDQOCV.json","view_paper":"https://pith.science/paper/HOCSZV4K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.11390&json=true","fetch_graph":"https://pith.science/api/pith-number/HOCSZV4KJQKKPDRS3FKLWDQOCV/graph.json","fetch_events":"https://pith.science/api/pith-number/HOCSZV4KJQKKPDRS3FKLWDQOCV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HOCSZV4KJQKKPDRS3FKLWDQOCV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HOCSZV4KJQKKPDRS3FKLWDQOCV/action/storage_attestation","attest_author":"https://pith.science/pith/HOCSZV4KJQKKPDRS3FKLWDQOCV/action/author_attestation","sign_citation":"https://pith.science/pith/HOCSZV4KJQKKPDRS3FKLWDQOCV/action/citation_signature","submit_replication":"https://pith.science/pith/HOCSZV4KJQKKPDRS3FKLWDQOCV/action/replication_record"}},"created_at":"2026-07-05T02:22:06.581090+00:00","updated_at":"2026-07-05T02:22:06.581090+00:00"}