{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ARCWTHN6Z2M5G2PCWKCKKZZFNO","short_pith_number":"pith:ARCWTHN6","schema_version":"1.0","canonical_sha256":"0445699dbece99d369e2b284a567256b8ff9cd16973e7a3889709d59dad9b545","source":{"kind":"arxiv","id":"2104.02281","version":1},"attestation_state":"computed","paper":{"title":"Learnable Expansion-and-Compression Network for Few-shot Class-Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binghao Liu, Boyu Yang, Chang Liu, Mengying Fu, Mingbao Lin, Qixiang Ye, Rongrong Ji","submitted_at":"2021-04-06T04:34:21Z","abstract_excerpt":"Few-shot class-incremental learning (FSCIL), which targets at continuously expanding model's representation capacity under few supervisions, is an important yet challenging problem. On the one hand, when fitting new tasks (novel classes), features trained on old tasks (old classes) could significantly drift, causing catastrophic forgetting. On the other hand, training the large amount of model parameters with few-shot novel-class examples leads to model over-fitting. In this paper, we propose a learnable expansion-and-compression network (LEC-Net), with the aim to simultaneously solve catastro"},"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":"2104.02281","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-06T04:34:21Z","cross_cats_sorted":[],"title_canon_sha256":"f3d42b1d22267eee0d907e94d81082662829817dd59f538f9509e94bc790f0b3","abstract_canon_sha256":"6d1075e7d7e32814dffef433eb4f591120768fb16e8d67f06745e885f5437990"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:29:16.528356Z","signature_b64":"AeJ1gmOErXvVnUdLmy2+ESQrLWaeaIPw5qq2GOvE0k5R0FMXJHhGdnoYYia1ADp4rUQVs+0GC93TgJd7sds8Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0445699dbece99d369e2b284a567256b8ff9cd16973e7a3889709d59dad9b545","last_reissued_at":"2026-07-05T02:29:16.527943Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:29:16.527943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learnable Expansion-and-Compression Network for Few-shot Class-Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binghao Liu, Boyu Yang, Chang Liu, Mengying Fu, Mingbao Lin, Qixiang Ye, Rongrong Ji","submitted_at":"2021-04-06T04:34:21Z","abstract_excerpt":"Few-shot class-incremental learning (FSCIL), which targets at continuously expanding model's representation capacity under few supervisions, is an important yet challenging problem. On the one hand, when fitting new tasks (novel classes), features trained on old tasks (old classes) could significantly drift, causing catastrophic forgetting. On the other hand, training the large amount of model parameters with few-shot novel-class examples leads to model over-fitting. In this paper, we propose a learnable expansion-and-compression network (LEC-Net), with the aim to simultaneously solve catastro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.02281","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/2104.02281/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":"2104.02281","created_at":"2026-07-05T02:29:16.528005+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.02281v1","created_at":"2026-07-05T02:29:16.528005+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.02281","created_at":"2026-07-05T02:29:16.528005+00:00"},{"alias_kind":"pith_short_12","alias_value":"ARCWTHN6Z2M5","created_at":"2026-07-05T02:29:16.528005+00:00"},{"alias_kind":"pith_short_16","alias_value":"ARCWTHN6Z2M5G2PC","created_at":"2026-07-05T02:29:16.528005+00:00"},{"alias_kind":"pith_short_8","alias_value":"ARCWTHN6","created_at":"2026-07-05T02:29:16.528005+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.09785","citing_title":"DSS-Prompt: Dynamic-Static Synergistic Prompting for Few-Shot Class-Incremental Learning","ref_index":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ARCWTHN6Z2M5G2PCWKCKKZZFNO","json":"https://pith.science/pith/ARCWTHN6Z2M5G2PCWKCKKZZFNO.json","graph_json":"https://pith.science/api/pith-number/ARCWTHN6Z2M5G2PCWKCKKZZFNO/graph.json","events_json":"https://pith.science/api/pith-number/ARCWTHN6Z2M5G2PCWKCKKZZFNO/events.json","paper":"https://pith.science/paper/ARCWTHN6"},"agent_actions":{"view_html":"https://pith.science/pith/ARCWTHN6Z2M5G2PCWKCKKZZFNO","download_json":"https://pith.science/pith/ARCWTHN6Z2M5G2PCWKCKKZZFNO.json","view_paper":"https://pith.science/paper/ARCWTHN6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.02281&json=true","fetch_graph":"https://pith.science/api/pith-number/ARCWTHN6Z2M5G2PCWKCKKZZFNO/graph.json","fetch_events":"https://pith.science/api/pith-number/ARCWTHN6Z2M5G2PCWKCKKZZFNO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ARCWTHN6Z2M5G2PCWKCKKZZFNO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ARCWTHN6Z2M5G2PCWKCKKZZFNO/action/storage_attestation","attest_author":"https://pith.science/pith/ARCWTHN6Z2M5G2PCWKCKKZZFNO/action/author_attestation","sign_citation":"https://pith.science/pith/ARCWTHN6Z2M5G2PCWKCKKZZFNO/action/citation_signature","submit_replication":"https://pith.science/pith/ARCWTHN6Z2M5G2PCWKCKKZZFNO/action/replication_record"}},"created_at":"2026-07-05T02:29:16.528005+00:00","updated_at":"2026-07-05T02:29:16.528005+00:00"}