{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:H6HA2YCJWKU66SE6NYJBZXEGE5","short_pith_number":"pith:H6HA2YCJ","schema_version":"1.0","canonical_sha256":"3f8e0d6049b2a9ef489e6e121cdc86275bf8087fb0f446949dbf2ed5854b6ede","source":{"kind":"arxiv","id":"2204.02136","version":1},"attestation_state":"computed","paper":{"title":"Overcoming Catastrophic Forgetting in Incremental Object Detection via Elastic Response Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hangjie Yuan, Mang Wang, Tao Feng","submitted_at":"2022-04-05T11:57:43Z","abstract_excerpt":"Traditional object detectors are ill-equipped for incremental learning. However, fine-tuning directly on a well-trained detection model with only new data will lead to catastrophic forgetting. Knowledge distillation is a flexible way to mitigate catastrophic forgetting. In Incremental Object Detection (IOD), previous work mainly focuses on distilling for the combination of features and responses. However, they under-explore the information that contains in responses. In this paper, we propose a response-based incremental distillation method, dubbed Elastic Response Distillation (ERD), which fo"},"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":"2204.02136","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-04-05T11:57:43Z","cross_cats_sorted":[],"title_canon_sha256":"9da316db3ce8e563b0d0de675d90d195ad96cc26d1695ec9853314b50a6960e3","abstract_canon_sha256":"417394e1f73235f8783684af07c9987dd1e8e2606dc89204f018b55de5e6ad95"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:11:36.947022Z","signature_b64":"Q/Btc+RGPJhfJc1RIQyFGd+mlGgyQQ9ahHjXV0NWQU5wMtLT2jIhB6qYK5gfvacZiv5oa7Fhq/ayvJu87zo+CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f8e0d6049b2a9ef489e6e121cdc86275bf8087fb0f446949dbf2ed5854b6ede","last_reissued_at":"2026-07-05T04:11:36.946628Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:11:36.946628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Overcoming Catastrophic Forgetting in Incremental Object Detection via Elastic Response Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hangjie Yuan, Mang Wang, Tao Feng","submitted_at":"2022-04-05T11:57:43Z","abstract_excerpt":"Traditional object detectors are ill-equipped for incremental learning. However, fine-tuning directly on a well-trained detection model with only new data will lead to catastrophic forgetting. Knowledge distillation is a flexible way to mitigate catastrophic forgetting. In Incremental Object Detection (IOD), previous work mainly focuses on distilling for the combination of features and responses. However, they under-explore the information that contains in responses. In this paper, we propose a response-based incremental distillation method, dubbed Elastic Response Distillation (ERD), which fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.02136","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/2204.02136/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":"2204.02136","created_at":"2026-07-05T04:11:36.946683+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.02136v1","created_at":"2026-07-05T04:11:36.946683+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.02136","created_at":"2026-07-05T04:11:36.946683+00:00"},{"alias_kind":"pith_short_12","alias_value":"H6HA2YCJWKU6","created_at":"2026-07-05T04:11:36.946683+00:00"},{"alias_kind":"pith_short_16","alias_value":"H6HA2YCJWKU66SE6","created_at":"2026-07-05T04:11:36.946683+00:00"},{"alias_kind":"pith_short_8","alias_value":"H6HA2YCJ","created_at":"2026-07-05T04:11:36.946683+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.11042","citing_title":"Improving Layout Representation Learning Across Inconsistently Annotated Datasets via Agentic Harmonization","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H6HA2YCJWKU66SE6NYJBZXEGE5","json":"https://pith.science/pith/H6HA2YCJWKU66SE6NYJBZXEGE5.json","graph_json":"https://pith.science/api/pith-number/H6HA2YCJWKU66SE6NYJBZXEGE5/graph.json","events_json":"https://pith.science/api/pith-number/H6HA2YCJWKU66SE6NYJBZXEGE5/events.json","paper":"https://pith.science/paper/H6HA2YCJ"},"agent_actions":{"view_html":"https://pith.science/pith/H6HA2YCJWKU66SE6NYJBZXEGE5","download_json":"https://pith.science/pith/H6HA2YCJWKU66SE6NYJBZXEGE5.json","view_paper":"https://pith.science/paper/H6HA2YCJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.02136&json=true","fetch_graph":"https://pith.science/api/pith-number/H6HA2YCJWKU66SE6NYJBZXEGE5/graph.json","fetch_events":"https://pith.science/api/pith-number/H6HA2YCJWKU66SE6NYJBZXEGE5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H6HA2YCJWKU66SE6NYJBZXEGE5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H6HA2YCJWKU66SE6NYJBZXEGE5/action/storage_attestation","attest_author":"https://pith.science/pith/H6HA2YCJWKU66SE6NYJBZXEGE5/action/author_attestation","sign_citation":"https://pith.science/pith/H6HA2YCJWKU66SE6NYJBZXEGE5/action/citation_signature","submit_replication":"https://pith.science/pith/H6HA2YCJWKU66SE6NYJBZXEGE5/action/replication_record"}},"created_at":"2026-07-05T04:11:36.946683+00:00","updated_at":"2026-07-05T04:11:36.946683+00:00"}