{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:DJ6QEGSCQB73RWA63TQYNQE3BD","short_pith_number":"pith:DJ6QEGSC","schema_version":"1.0","canonical_sha256":"1a7d021a42807fb8d81edce186c09b08d2631385274932fd3c15de7b9e728c55","source":{"kind":"arxiv","id":"1412.6856","version":2},"attestation_state":"computed","paper":{"title":"Object Detectors Emerge in Deep Scene CNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.CV","authors_text":"Aditya Khosla, Agata Lapedriza, Antonio Torralba, Aude Oliva, Bolei Zhou","submitted_at":"2014-12-22T01:14:01Z","abstract_excerpt":"With the success of new computational architectures for visual processing, such as convolutional neural networks (CNN) and access to image databases with millions of labeled examples (e.g., ImageNet, Places), the state of the art in computer vision is advancing rapidly. One important factor for continued progress is to understand the representations that are learned by the inner layers of these deep architectures. Here we show that object detectors emerge from training CNNs to perform scene classification. As scenes are composed of objects, the CNN for scene classification automatically discov"},"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":"1412.6856","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-12-22T01:14:01Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"67b03bbd7440fb08ae26e2a91fc622b5e70566313c47977ae0882a131476b74d","abstract_canon_sha256":"c42c1cb2ee2dd71e4deacac9ae8b06ba249f33e9bbcda688e7e21f303292896f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:18:43.075186Z","signature_b64":"FHGa3T9UK9bOemlpe0pDgCpJHXU2971fjvsWe6BA+jPfpBahCYpNMwNlvQym3hFbMB9itJaVLNK/G93gCSxEAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a7d021a42807fb8d81edce186c09b08d2631385274932fd3c15de7b9e728c55","last_reissued_at":"2026-05-18T02:18:43.074530Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:18:43.074530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Object Detectors Emerge in Deep Scene CNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.CV","authors_text":"Aditya Khosla, Agata Lapedriza, Antonio Torralba, Aude Oliva, Bolei Zhou","submitted_at":"2014-12-22T01:14:01Z","abstract_excerpt":"With the success of new computational architectures for visual processing, such as convolutional neural networks (CNN) and access to image databases with millions of labeled examples (e.g., ImageNet, Places), the state of the art in computer vision is advancing rapidly. One important factor for continued progress is to understand the representations that are learned by the inner layers of these deep architectures. Here we show that object detectors emerge from training CNNs to perform scene classification. As scenes are composed of objects, the CNN for scene classification automatically discov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.6856","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":""},"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":"1412.6856","created_at":"2026-05-18T02:18:43.074630+00:00"},{"alias_kind":"arxiv_version","alias_value":"1412.6856v2","created_at":"2026-05-18T02:18:43.074630+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.6856","created_at":"2026-05-18T02:18:43.074630+00:00"},{"alias_kind":"pith_short_12","alias_value":"DJ6QEGSCQB73","created_at":"2026-05-18T12:28:25.294606+00:00"},{"alias_kind":"pith_short_16","alias_value":"DJ6QEGSCQB73RWA6","created_at":"2026-05-18T12:28:25.294606+00:00"},{"alias_kind":"pith_short_8","alias_value":"DJ6QEGSC","created_at":"2026-05-18T12:28:25.294606+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2502.20349","citing_title":"Naturalistic Computational Cognitive Science: Towards generalizable models and theories that capture the full range of natural behavior","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"1907.08514","citing_title":"Predicting Visual Memory Schemas with Variational Autoencoders","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2312.03508","citing_title":"Convolutional neural network based decoders for surface codes","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2502.20349","citing_title":"Naturalistic Computational Cognitive Science: Towards generalizable models and theories that capture the full range of natural behavior","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2209.10652","citing_title":"Toy Models of Superposition","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07831","citing_title":"Explainable Part-Based Vehicle Classifier with Spatial Awareness","ref_index":75,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DJ6QEGSCQB73RWA63TQYNQE3BD","json":"https://pith.science/pith/DJ6QEGSCQB73RWA63TQYNQE3BD.json","graph_json":"https://pith.science/api/pith-number/DJ6QEGSCQB73RWA63TQYNQE3BD/graph.json","events_json":"https://pith.science/api/pith-number/DJ6QEGSCQB73RWA63TQYNQE3BD/events.json","paper":"https://pith.science/paper/DJ6QEGSC"},"agent_actions":{"view_html":"https://pith.science/pith/DJ6QEGSCQB73RWA63TQYNQE3BD","download_json":"https://pith.science/pith/DJ6QEGSCQB73RWA63TQYNQE3BD.json","view_paper":"https://pith.science/paper/DJ6QEGSC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1412.6856&json=true","fetch_graph":"https://pith.science/api/pith-number/DJ6QEGSCQB73RWA63TQYNQE3BD/graph.json","fetch_events":"https://pith.science/api/pith-number/DJ6QEGSCQB73RWA63TQYNQE3BD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DJ6QEGSCQB73RWA63TQYNQE3BD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DJ6QEGSCQB73RWA63TQYNQE3BD/action/storage_attestation","attest_author":"https://pith.science/pith/DJ6QEGSCQB73RWA63TQYNQE3BD/action/author_attestation","sign_citation":"https://pith.science/pith/DJ6QEGSCQB73RWA63TQYNQE3BD/action/citation_signature","submit_replication":"https://pith.science/pith/DJ6QEGSCQB73RWA63TQYNQE3BD/action/replication_record"}},"created_at":"2026-05-18T02:18:43.074630+00:00","updated_at":"2026-05-18T02:18:43.074630+00:00"}