{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ILKSGS65D4X5SYEYXDZ6PC6EAH","short_pith_number":"pith:ILKSGS65","schema_version":"1.0","canonical_sha256":"42d5234bdd1f2fd96098b8f3e78bc401e832eed984feaf41f74731a82e1a5bb6","source":{"kind":"arxiv","id":"2304.04620","version":1},"attestation_state":"computed","paper":{"title":"Federated Incremental Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dengxin Dai, Duzhen Zhang, Henghui Ding, Jiahua Dong, Wei Cong, Yang Cong","submitted_at":"2023-04-10T14:34:23Z","abstract_excerpt":"Federated learning-based semantic segmentation (FSS) has drawn widespread attention via decentralized training on local clients. However, most FSS models assume categories are fixed in advance, thus heavily undergoing forgetting on old categories in practical applications where local clients receive new categories incrementally while have no memory storage to access old classes. Moreover, new clients collecting novel classes may join in the global training of FSS, which further exacerbates catastrophic forgetting. To surmount the above challenges, we propose a Forgetting-Balanced Learning (FBL"},"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":"2304.04620","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-10T14:34:23Z","cross_cats_sorted":[],"title_canon_sha256":"7e1f3f2a7f855061317d99f076e0778f355cf991eb022be3c8486a7f3dc6d11a","abstract_canon_sha256":"3040a996a128db9d767a5e3a9fa380512b423298958bb9e78776bfb70ce025eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:59:28.246635Z","signature_b64":"RUjLk1oAF5jw4/m5Zd2sSklzx19ksXghdpe7gKG8KXbMdtb6Mpd3achA8M0i1ZYyq7KHbYv9I0V2lPocSzwqDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42d5234bdd1f2fd96098b8f3e78bc401e832eed984feaf41f74731a82e1a5bb6","last_reissued_at":"2026-07-05T05:59:28.246202Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:59:28.246202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Incremental Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dengxin Dai, Duzhen Zhang, Henghui Ding, Jiahua Dong, Wei Cong, Yang Cong","submitted_at":"2023-04-10T14:34:23Z","abstract_excerpt":"Federated learning-based semantic segmentation (FSS) has drawn widespread attention via decentralized training on local clients. However, most FSS models assume categories are fixed in advance, thus heavily undergoing forgetting on old categories in practical applications where local clients receive new categories incrementally while have no memory storage to access old classes. Moreover, new clients collecting novel classes may join in the global training of FSS, which further exacerbates catastrophic forgetting. To surmount the above challenges, we propose a Forgetting-Balanced Learning (FBL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.04620","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/2304.04620/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":"2304.04620","created_at":"2026-07-05T05:59:28.246265+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.04620v1","created_at":"2026-07-05T05:59:28.246265+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.04620","created_at":"2026-07-05T05:59:28.246265+00:00"},{"alias_kind":"pith_short_12","alias_value":"ILKSGS65D4X5","created_at":"2026-07-05T05:59:28.246265+00:00"},{"alias_kind":"pith_short_16","alias_value":"ILKSGS65D4X5SYEY","created_at":"2026-07-05T05:59:28.246265+00:00"},{"alias_kind":"pith_short_8","alias_value":"ILKSGS65","created_at":"2026-07-05T05:59:28.246265+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/ILKSGS65D4X5SYEYXDZ6PC6EAH","json":"https://pith.science/pith/ILKSGS65D4X5SYEYXDZ6PC6EAH.json","graph_json":"https://pith.science/api/pith-number/ILKSGS65D4X5SYEYXDZ6PC6EAH/graph.json","events_json":"https://pith.science/api/pith-number/ILKSGS65D4X5SYEYXDZ6PC6EAH/events.json","paper":"https://pith.science/paper/ILKSGS65"},"agent_actions":{"view_html":"https://pith.science/pith/ILKSGS65D4X5SYEYXDZ6PC6EAH","download_json":"https://pith.science/pith/ILKSGS65D4X5SYEYXDZ6PC6EAH.json","view_paper":"https://pith.science/paper/ILKSGS65","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.04620&json=true","fetch_graph":"https://pith.science/api/pith-number/ILKSGS65D4X5SYEYXDZ6PC6EAH/graph.json","fetch_events":"https://pith.science/api/pith-number/ILKSGS65D4X5SYEYXDZ6PC6EAH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ILKSGS65D4X5SYEYXDZ6PC6EAH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ILKSGS65D4X5SYEYXDZ6PC6EAH/action/storage_attestation","attest_author":"https://pith.science/pith/ILKSGS65D4X5SYEYXDZ6PC6EAH/action/author_attestation","sign_citation":"https://pith.science/pith/ILKSGS65D4X5SYEYXDZ6PC6EAH/action/citation_signature","submit_replication":"https://pith.science/pith/ILKSGS65D4X5SYEYXDZ6PC6EAH/action/replication_record"}},"created_at":"2026-07-05T05:59:28.246265+00:00","updated_at":"2026-07-05T05:59:28.246265+00:00"}