{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BUQ34ZTBYBFKLC3HXZSJQC3TVI","short_pith_number":"pith:BUQ34ZTB","schema_version":"1.0","canonical_sha256":"0d21be6661c04aa58b67be64980b73aa008c757a84226aa22adb93d2b1f27705","source":{"kind":"arxiv","id":"2210.05941","version":1},"attestation_state":"computed","paper":{"title":"Decomposed Knowledge Distillation for Class-Incremental Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bumsub Ham, DongHyeon Baek, Junghyup Lee, Sanghoon Lee, Youngmin Oh","submitted_at":"2022-10-12T06:15:51Z","abstract_excerpt":"Class-incremental semantic segmentation (CISS) labels each pixel of an image with a corresponding object/stuff class continually. To this end, it is crucial to learn novel classes incrementally without forgetting previously learned knowledge. Current CISS methods typically use a knowledge distillation (KD) technique for preserving classifier logits, or freeze a feature extractor, to avoid the forgetting problem. The strong constraints, however, prevent learning discriminative features for novel classes. We introduce a CISS framework that alleviates the forgetting problem and facilitates learni"},"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":"2210.05941","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-12T06:15:51Z","cross_cats_sorted":[],"title_canon_sha256":"9b68dd1ceedba60941969e88604059618c179ce8985dfb61bac0824203f5ffaf","abstract_canon_sha256":"a2fc71ff355a8ce60d018951081027bf688feda8b11f350c5076f4b8fe2461cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:05:54.702640Z","signature_b64":"5dJQHJj0z1MfOa0CtbTi3Xrxh3dwpQGMU9lhVjpevif17CPpKOiA+FfDW/LL3rarwNJTEVDOrqOX4fLuynUyBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d21be6661c04aa58b67be64980b73aa008c757a84226aa22adb93d2b1f27705","last_reissued_at":"2026-07-05T05:05:54.702116Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:05:54.702116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decomposed Knowledge Distillation for Class-Incremental Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bumsub Ham, DongHyeon Baek, Junghyup Lee, Sanghoon Lee, Youngmin Oh","submitted_at":"2022-10-12T06:15:51Z","abstract_excerpt":"Class-incremental semantic segmentation (CISS) labels each pixel of an image with a corresponding object/stuff class continually. To this end, it is crucial to learn novel classes incrementally without forgetting previously learned knowledge. Current CISS methods typically use a knowledge distillation (KD) technique for preserving classifier logits, or freeze a feature extractor, to avoid the forgetting problem. The strong constraints, however, prevent learning discriminative features for novel classes. We introduce a CISS framework that alleviates the forgetting problem and facilitates learni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05941","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/2210.05941/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":"2210.05941","created_at":"2026-07-05T05:05:54.702181+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.05941v1","created_at":"2026-07-05T05:05:54.702181+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05941","created_at":"2026-07-05T05:05:54.702181+00:00"},{"alias_kind":"pith_short_12","alias_value":"BUQ34ZTBYBFK","created_at":"2026-07-05T05:05:54.702181+00:00"},{"alias_kind":"pith_short_16","alias_value":"BUQ34ZTBYBFKLC3H","created_at":"2026-07-05T05:05:54.702181+00:00"},{"alias_kind":"pith_short_8","alias_value":"BUQ34ZTB","created_at":"2026-07-05T05:05:54.702181+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00527","citing_title":"Learning Yourself: Class-Incremental Semantic Segmentation with Language-Inspired Bootstrapped Disentanglement","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BUQ34ZTBYBFKLC3HXZSJQC3TVI","json":"https://pith.science/pith/BUQ34ZTBYBFKLC3HXZSJQC3TVI.json","graph_json":"https://pith.science/api/pith-number/BUQ34ZTBYBFKLC3HXZSJQC3TVI/graph.json","events_json":"https://pith.science/api/pith-number/BUQ34ZTBYBFKLC3HXZSJQC3TVI/events.json","paper":"https://pith.science/paper/BUQ34ZTB"},"agent_actions":{"view_html":"https://pith.science/pith/BUQ34ZTBYBFKLC3HXZSJQC3TVI","download_json":"https://pith.science/pith/BUQ34ZTBYBFKLC3HXZSJQC3TVI.json","view_paper":"https://pith.science/paper/BUQ34ZTB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.05941&json=true","fetch_graph":"https://pith.science/api/pith-number/BUQ34ZTBYBFKLC3HXZSJQC3TVI/graph.json","fetch_events":"https://pith.science/api/pith-number/BUQ34ZTBYBFKLC3HXZSJQC3TVI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BUQ34ZTBYBFKLC3HXZSJQC3TVI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BUQ34ZTBYBFKLC3HXZSJQC3TVI/action/storage_attestation","attest_author":"https://pith.science/pith/BUQ34ZTBYBFKLC3HXZSJQC3TVI/action/author_attestation","sign_citation":"https://pith.science/pith/BUQ34ZTBYBFKLC3HXZSJQC3TVI/action/citation_signature","submit_replication":"https://pith.science/pith/BUQ34ZTBYBFKLC3HXZSJQC3TVI/action/replication_record"}},"created_at":"2026-07-05T05:05:54.702181+00:00","updated_at":"2026-07-05T05:05:54.702181+00:00"}