{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:D7WVABEOP6IX6QNSRI5GNIEPFA","short_pith_number":"pith:D7WVABEO","schema_version":"1.0","canonical_sha256":"1fed50048e7f917f41b28a3a66a08f283be3160f3bdffa89f57eb30781d83846","source":{"kind":"arxiv","id":"1805.09300","version":3},"attestation_state":"computed","paper":{"title":"SNIPER: Efficient Multi-Scale Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bharat Singh, Larry S. Davis, Mahyar Najibi","submitted_at":"2018-05-23T17:38:27Z","abstract_excerpt":"We present SNIPER, an algorithm for performing efficient multi-scale training in instance level visual recognition tasks. Instead of processing every pixel in an image pyramid, SNIPER processes context regions around ground-truth instances (referred to as chips) at the appropriate scale. For background sampling, these context-regions are generated using proposals extracted from a region proposal network trained with a short learning schedule. Hence, the number of chips generated per image during training adaptively changes based on the scene complexity. SNIPER only processes 30% more pixels co"},"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":"1805.09300","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-23T17:38:27Z","cross_cats_sorted":[],"title_canon_sha256":"0aaac90defaa8fb6f0f238c273543722831e92e2a0b1badb3cadd8e92f2f36d9","abstract_canon_sha256":"659d79f3ac9bf8fd06a78cf4e9ee827a658def36404674c6cf64621ad2ebed3d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:23.016130Z","signature_b64":"RZCUFqpcFlzTlTAX7r7g7GdQmtlx9+HE4ADV8Ba6X6sfiutsQrQIZNhx92n6r+0lF4WFEqBZc1cToy8GbpdeDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1fed50048e7f917f41b28a3a66a08f283be3160f3bdffa89f57eb30781d83846","last_reissued_at":"2026-05-17T23:58:23.015332Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:23.015332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SNIPER: Efficient Multi-Scale Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bharat Singh, Larry S. Davis, Mahyar Najibi","submitted_at":"2018-05-23T17:38:27Z","abstract_excerpt":"We present SNIPER, an algorithm for performing efficient multi-scale training in instance level visual recognition tasks. Instead of processing every pixel in an image pyramid, SNIPER processes context regions around ground-truth instances (referred to as chips) at the appropriate scale. For background sampling, these context-regions are generated using proposals extracted from a region proposal network trained with a short learning schedule. Hence, the number of chips generated per image during training adaptively changes based on the scene complexity. SNIPER only processes 30% more pixels co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09300","kind":"arxiv","version":3},"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":"1805.09300","created_at":"2026-05-17T23:58:23.015463+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.09300v3","created_at":"2026-05-17T23:58:23.015463+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09300","created_at":"2026-05-17T23:58:23.015463+00:00"},{"alias_kind":"pith_short_12","alias_value":"D7WVABEOP6IX","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"D7WVABEOP6IX6QNS","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"D7WVABEO","created_at":"2026-05-18T12:32:19.392346+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.25300","citing_title":"DenseScout: Algorithm-System Co-design for Budgeted Tiny Object Selection on Edge Platforms","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D7WVABEOP6IX6QNSRI5GNIEPFA","json":"https://pith.science/pith/D7WVABEOP6IX6QNSRI5GNIEPFA.json","graph_json":"https://pith.science/api/pith-number/D7WVABEOP6IX6QNSRI5GNIEPFA/graph.json","events_json":"https://pith.science/api/pith-number/D7WVABEOP6IX6QNSRI5GNIEPFA/events.json","paper":"https://pith.science/paper/D7WVABEO"},"agent_actions":{"view_html":"https://pith.science/pith/D7WVABEOP6IX6QNSRI5GNIEPFA","download_json":"https://pith.science/pith/D7WVABEOP6IX6QNSRI5GNIEPFA.json","view_paper":"https://pith.science/paper/D7WVABEO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.09300&json=true","fetch_graph":"https://pith.science/api/pith-number/D7WVABEOP6IX6QNSRI5GNIEPFA/graph.json","fetch_events":"https://pith.science/api/pith-number/D7WVABEOP6IX6QNSRI5GNIEPFA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D7WVABEOP6IX6QNSRI5GNIEPFA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D7WVABEOP6IX6QNSRI5GNIEPFA/action/storage_attestation","attest_author":"https://pith.science/pith/D7WVABEOP6IX6QNSRI5GNIEPFA/action/author_attestation","sign_citation":"https://pith.science/pith/D7WVABEOP6IX6QNSRI5GNIEPFA/action/citation_signature","submit_replication":"https://pith.science/pith/D7WVABEOP6IX6QNSRI5GNIEPFA/action/replication_record"}},"created_at":"2026-05-17T23:58:23.015463+00:00","updated_at":"2026-05-17T23:58:23.015463+00:00"}