{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:PJEWDGRLSQRDB6MEJXWDLDVMAO","short_pith_number":"pith:PJEWDGRL","schema_version":"1.0","canonical_sha256":"7a49619a2b942230f9844dec358eac03ac41d35be031809169bb8a89c74fb13e","source":{"kind":"arxiv","id":"1606.02819","version":4},"attestation_state":"computed","paper":{"title":"Low-shot Visual Recognition by Shrinking and Hallucinating Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bharath Hariharan, Ross Girshick","submitted_at":"2016-06-09T04:28:07Z","abstract_excerpt":"Low-shot visual learning---the ability to recognize novel object categories from very few examples---is a hallmark of human visual intelligence. Existing machine learning approaches fail to generalize in the same way. To make progress on this foundational problem, we present a low-shot learning benchmark on complex images that mimics challenges faced by recognition systems in the wild. We then propose a) representation regularization techniques, and b) techniques to hallucinate additional training examples for data-starved classes. Together, our methods improve the effectiveness of convolution"},"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":"1606.02819","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-06-09T04:28:07Z","cross_cats_sorted":[],"title_canon_sha256":"50c268a6252a32be8874fa4ed8dd5e583e5179e480b26d30054865969298449b","abstract_canon_sha256":"54fd487c65e90b06b4758540249dc4169a96290a3f958b86d82883b3df24e7d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:22.614030Z","signature_b64":"0uelhgGhQNkj7W8Fe2tFTXdx4+v5/cl6JDVrclN2fe9zIhL2j+a7v3zGUqviptRrouZ7PmPyhEY4oChg6N/WBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a49619a2b942230f9844dec358eac03ac41d35be031809169bb8a89c74fb13e","last_reissued_at":"2026-05-18T00:31:22.613511Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:22.613511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Low-shot Visual Recognition by Shrinking and Hallucinating Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bharath Hariharan, Ross Girshick","submitted_at":"2016-06-09T04:28:07Z","abstract_excerpt":"Low-shot visual learning---the ability to recognize novel object categories from very few examples---is a hallmark of human visual intelligence. Existing machine learning approaches fail to generalize in the same way. To make progress on this foundational problem, we present a low-shot learning benchmark on complex images that mimics challenges faced by recognition systems in the wild. We then propose a) representation regularization techniques, and b) techniques to hallucinate additional training examples for data-starved classes. Together, our methods improve the effectiveness of convolution"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.02819","kind":"arxiv","version":4},"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":"1606.02819","created_at":"2026-05-18T00:31:22.613585+00:00"},{"alias_kind":"arxiv_version","alias_value":"1606.02819v4","created_at":"2026-05-18T00:31:22.613585+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.02819","created_at":"2026-05-18T00:31:22.613585+00:00"},{"alias_kind":"pith_short_12","alias_value":"PJEWDGRLSQRD","created_at":"2026-05-18T12:30:39.010887+00:00"},{"alias_kind":"pith_short_16","alias_value":"PJEWDGRLSQRDB6ME","created_at":"2026-05-18T12:30:39.010887+00:00"},{"alias_kind":"pith_short_8","alias_value":"PJEWDGRL","created_at":"2026-05-18T12:30:39.010887+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.07844","citing_title":"Growing a Brain: Fine-Tuning by Increasing Model Capacity","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PJEWDGRLSQRDB6MEJXWDLDVMAO","json":"https://pith.science/pith/PJEWDGRLSQRDB6MEJXWDLDVMAO.json","graph_json":"https://pith.science/api/pith-number/PJEWDGRLSQRDB6MEJXWDLDVMAO/graph.json","events_json":"https://pith.science/api/pith-number/PJEWDGRLSQRDB6MEJXWDLDVMAO/events.json","paper":"https://pith.science/paper/PJEWDGRL"},"agent_actions":{"view_html":"https://pith.science/pith/PJEWDGRLSQRDB6MEJXWDLDVMAO","download_json":"https://pith.science/pith/PJEWDGRLSQRDB6MEJXWDLDVMAO.json","view_paper":"https://pith.science/paper/PJEWDGRL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1606.02819&json=true","fetch_graph":"https://pith.science/api/pith-number/PJEWDGRLSQRDB6MEJXWDLDVMAO/graph.json","fetch_events":"https://pith.science/api/pith-number/PJEWDGRLSQRDB6MEJXWDLDVMAO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PJEWDGRLSQRDB6MEJXWDLDVMAO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PJEWDGRLSQRDB6MEJXWDLDVMAO/action/storage_attestation","attest_author":"https://pith.science/pith/PJEWDGRLSQRDB6MEJXWDLDVMAO/action/author_attestation","sign_citation":"https://pith.science/pith/PJEWDGRLSQRDB6MEJXWDLDVMAO/action/citation_signature","submit_replication":"https://pith.science/pith/PJEWDGRLSQRDB6MEJXWDLDVMAO/action/replication_record"}},"created_at":"2026-05-18T00:31:22.613585+00:00","updated_at":"2026-05-18T00:31:22.613585+00:00"}