{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:FKVCRWJH6B33ZAZ2BTAGJZ55UT","short_pith_number":"pith:FKVCRWJH","schema_version":"1.0","canonical_sha256":"2aaa28d927f077bc833a0cc064e7bda4dd6b7efea0ba9dcc299ea81f65ab9057","source":{"kind":"arxiv","id":"1903.05050","version":1},"attestation_state":"computed","paper":{"title":"Dense Classification and Implanting for Few-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrei Bursuc, Sylvaine Picard, Yannis Avrithis, Yann Lifchitz","submitted_at":"2019-03-12T16:58:08Z","abstract_excerpt":"Training deep neural networks from few examples is a highly challenging and key problem for many computer vision tasks. In this context, we are targeting knowledge transfer from a set with abundant data to other sets with few available examples. We propose two simple and effective solutions: (i) dense classification over feature maps, which for the first time studies local activations in the domain of few-shot learning, and (ii) implanting, that is, attaching new neurons to a previously trained network to learn new, task-specific features. On miniImageNet, we improve the prior state-of-the-art"},"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":"1903.05050","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-12T16:58:08Z","cross_cats_sorted":[],"title_canon_sha256":"ae9e4853a65936140cc12bb35728bf9d9e51bd84f97d8edc98ffaa2db2320fd3","abstract_canon_sha256":"d4a75dac1bc26f0109c67209c035fc2de8a4bb4110d816cd1edca9693c3f676f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:26.439825Z","signature_b64":"H81trxSKfLRm4RS6F9z6A4d4wu8Wze7utPSjNduEatmYlK65Kod36pu8XUCoWfctsMcbqW7EMYqpOe7x4oepDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2aaa28d927f077bc833a0cc064e7bda4dd6b7efea0ba9dcc299ea81f65ab9057","last_reissued_at":"2026-05-17T23:51:26.439311Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:26.439311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dense Classification and Implanting for Few-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrei Bursuc, Sylvaine Picard, Yannis Avrithis, Yann Lifchitz","submitted_at":"2019-03-12T16:58:08Z","abstract_excerpt":"Training deep neural networks from few examples is a highly challenging and key problem for many computer vision tasks. In this context, we are targeting knowledge transfer from a set with abundant data to other sets with few available examples. We propose two simple and effective solutions: (i) dense classification over feature maps, which for the first time studies local activations in the domain of few-shot learning, and (ii) implanting, that is, attaching new neurons to a previously trained network to learn new, task-specific features. On miniImageNet, we improve the prior state-of-the-art"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.05050","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":""},"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":"1903.05050","created_at":"2026-05-17T23:51:26.439405+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.05050v1","created_at":"2026-05-17T23:51:26.439405+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.05050","created_at":"2026-05-17T23:51:26.439405+00:00"},{"alias_kind":"pith_short_12","alias_value":"FKVCRWJH6B33","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"FKVCRWJH6B33ZAZ2","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"FKVCRWJH","created_at":"2026-05-18T12:33:15.570797+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/FKVCRWJH6B33ZAZ2BTAGJZ55UT","json":"https://pith.science/pith/FKVCRWJH6B33ZAZ2BTAGJZ55UT.json","graph_json":"https://pith.science/api/pith-number/FKVCRWJH6B33ZAZ2BTAGJZ55UT/graph.json","events_json":"https://pith.science/api/pith-number/FKVCRWJH6B33ZAZ2BTAGJZ55UT/events.json","paper":"https://pith.science/paper/FKVCRWJH"},"agent_actions":{"view_html":"https://pith.science/pith/FKVCRWJH6B33ZAZ2BTAGJZ55UT","download_json":"https://pith.science/pith/FKVCRWJH6B33ZAZ2BTAGJZ55UT.json","view_paper":"https://pith.science/paper/FKVCRWJH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.05050&json=true","fetch_graph":"https://pith.science/api/pith-number/FKVCRWJH6B33ZAZ2BTAGJZ55UT/graph.json","fetch_events":"https://pith.science/api/pith-number/FKVCRWJH6B33ZAZ2BTAGJZ55UT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FKVCRWJH6B33ZAZ2BTAGJZ55UT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FKVCRWJH6B33ZAZ2BTAGJZ55UT/action/storage_attestation","attest_author":"https://pith.science/pith/FKVCRWJH6B33ZAZ2BTAGJZ55UT/action/author_attestation","sign_citation":"https://pith.science/pith/FKVCRWJH6B33ZAZ2BTAGJZ55UT/action/citation_signature","submit_replication":"https://pith.science/pith/FKVCRWJH6B33ZAZ2BTAGJZ55UT/action/replication_record"}},"created_at":"2026-05-17T23:51:26.439405+00:00","updated_at":"2026-05-17T23:51:26.439405+00:00"}