{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ERFNYD3K5BFSAJBARDJIE2O3W5","short_pith_number":"pith:ERFNYD3K","schema_version":"1.0","canonical_sha256":"244adc0f6ae84b20242088d28269dbb74856178a9e12c26a4c6cb890f07f3295","source":{"kind":"arxiv","id":"2006.09785","version":2},"attestation_state":"computed","paper":{"title":"Self-supervised Knowledge Distillation for Few-shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fahad Shahbaz Khan, Jathushan Rajasegaran, Mubarak Shah, Munawar Hayat, Salman Khan","submitted_at":"2020-06-17T11:27:00Z","abstract_excerpt":"Real-world contains an overwhelmingly large number of object classes, learning all of which at once is infeasible. Few shot learning is a promising learning paradigm due to its ability to learn out of order distributions quickly with only a few samples. Recent works [7, 41] show that simply learning a good feature embedding can outperform more sophisticated meta-learning and metric learning algorithms for few-shot learning. In this paper, we propose a simple approach to improve the representation capacity of deep neural networks for few-shot learning tasks. We follow a two-stage learning proce"},"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":"2006.09785","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-17T11:27:00Z","cross_cats_sorted":[],"title_canon_sha256":"afe3a7e6ad79acb084cf2807b7b415e40a373d6210c076b3ce1f80c76d3b83dd","abstract_canon_sha256":"6349e46080d568990ae2009385b3ebf7270c0295cfab38547171b2485086622d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:24:16.652553Z","signature_b64":"tmdaEsYcQlTVluWXmWUE/uie0PmcQeRKDuiep78G8OWeP2bAJx4hRHExbIdjM8LD+vwGjG7x+IRZb3xi6LWRAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"244adc0f6ae84b20242088d28269dbb74856178a9e12c26a4c6cb890f07f3295","last_reissued_at":"2026-07-05T01:24:16.652068Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:24:16.652068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-supervised Knowledge Distillation for Few-shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fahad Shahbaz Khan, Jathushan Rajasegaran, Mubarak Shah, Munawar Hayat, Salman Khan","submitted_at":"2020-06-17T11:27:00Z","abstract_excerpt":"Real-world contains an overwhelmingly large number of object classes, learning all of which at once is infeasible. Few shot learning is a promising learning paradigm due to its ability to learn out of order distributions quickly with only a few samples. Recent works [7, 41] show that simply learning a good feature embedding can outperform more sophisticated meta-learning and metric learning algorithms for few-shot learning. In this paper, we propose a simple approach to improve the representation capacity of deep neural networks for few-shot learning tasks. We follow a two-stage learning proce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.09785","kind":"arxiv","version":2},"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/2006.09785/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":"2006.09785","created_at":"2026-07-05T01:24:16.652126+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.09785v2","created_at":"2026-07-05T01:24:16.652126+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.09785","created_at":"2026-07-05T01:24:16.652126+00:00"},{"alias_kind":"pith_short_12","alias_value":"ERFNYD3K5BFS","created_at":"2026-07-05T01:24:16.652126+00:00"},{"alias_kind":"pith_short_16","alias_value":"ERFNYD3K5BFSAJBA","created_at":"2026-07-05T01:24:16.652126+00:00"},{"alias_kind":"pith_short_8","alias_value":"ERFNYD3K","created_at":"2026-07-05T01:24:16.652126+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.03841","citing_title":"Training a Student Expert via Semi-Supervised Foundation Model Distillation","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ERFNYD3K5BFSAJBARDJIE2O3W5","json":"https://pith.science/pith/ERFNYD3K5BFSAJBARDJIE2O3W5.json","graph_json":"https://pith.science/api/pith-number/ERFNYD3K5BFSAJBARDJIE2O3W5/graph.json","events_json":"https://pith.science/api/pith-number/ERFNYD3K5BFSAJBARDJIE2O3W5/events.json","paper":"https://pith.science/paper/ERFNYD3K"},"agent_actions":{"view_html":"https://pith.science/pith/ERFNYD3K5BFSAJBARDJIE2O3W5","download_json":"https://pith.science/pith/ERFNYD3K5BFSAJBARDJIE2O3W5.json","view_paper":"https://pith.science/paper/ERFNYD3K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.09785&json=true","fetch_graph":"https://pith.science/api/pith-number/ERFNYD3K5BFSAJBARDJIE2O3W5/graph.json","fetch_events":"https://pith.science/api/pith-number/ERFNYD3K5BFSAJBARDJIE2O3W5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ERFNYD3K5BFSAJBARDJIE2O3W5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ERFNYD3K5BFSAJBARDJIE2O3W5/action/storage_attestation","attest_author":"https://pith.science/pith/ERFNYD3K5BFSAJBARDJIE2O3W5/action/author_attestation","sign_citation":"https://pith.science/pith/ERFNYD3K5BFSAJBARDJIE2O3W5/action/citation_signature","submit_replication":"https://pith.science/pith/ERFNYD3K5BFSAJBARDJIE2O3W5/action/replication_record"}},"created_at":"2026-07-05T01:24:16.652126+00:00","updated_at":"2026-07-05T01:24:16.652126+00:00"}