{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NDFL6E6SP63E5WVVFO2SYOVWUV","short_pith_number":"pith:NDFL6E6S","schema_version":"1.0","canonical_sha256":"68cabf13d27fb64edab52bb52c3ab6a5791f794ea9950628c691acfaa2eb5228","source":{"kind":"arxiv","id":"2111.00674","version":4},"attestation_state":"computed","paper":{"title":"Distilling Object Detectors with Feature Richness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ming Chang, Rui Zhang, Shaoli Liu, Tianshi Chen, Xishan Zhang, Yunji Chen, Zhixing Du","submitted_at":"2021-11-01T03:16:06Z","abstract_excerpt":"In recent years, large-scale deep models have achieved great success, but the huge computational complexity and massive storage requirements make it a great challenge to deploy them in resource-limited devices. As a model compression and acceleration method, knowledge distillation effectively improves the performance of small models by transferring the dark knowledge from the teacher detector. However, most of the existing distillation-based detection methods mainly imitating features near bounding boxes, which suffer from two limitations. First, they ignore the beneficial features outside the"},"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":"2111.00674","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-01T03:16:06Z","cross_cats_sorted":[],"title_canon_sha256":"4632fe6647f73ed15ca3f9aec4fe8e6e46b5ff61b100e87e4d5dab09867b1e03","abstract_canon_sha256":"6a33a11b794aa27d5bdf57ad7da34fac65b847e05fbc9eb09cc26a39dc00c05b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:41:41.695896Z","signature_b64":"lXfSOZGWJ1xwfLVLJhkkCxtCSeUmzGJRnMW4IJNL3E5WaP4g/1Uu3jmVZAGwdNTyN5SA1v6k4CoOoWdLWN73Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68cabf13d27fb64edab52bb52c3ab6a5791f794ea9950628c691acfaa2eb5228","last_reissued_at":"2026-07-05T03:41:41.695413Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:41:41.695413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distilling Object Detectors with Feature Richness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ming Chang, Rui Zhang, Shaoli Liu, Tianshi Chen, Xishan Zhang, Yunji Chen, Zhixing Du","submitted_at":"2021-11-01T03:16:06Z","abstract_excerpt":"In recent years, large-scale deep models have achieved great success, but the huge computational complexity and massive storage requirements make it a great challenge to deploy them in resource-limited devices. As a model compression and acceleration method, knowledge distillation effectively improves the performance of small models by transferring the dark knowledge from the teacher detector. However, most of the existing distillation-based detection methods mainly imitating features near bounding boxes, which suffer from two limitations. First, they ignore the beneficial features outside the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.00674","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2111.00674/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":"2111.00674","created_at":"2026-07-05T03:41:41.695470+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.00674v4","created_at":"2026-07-05T03:41:41.695470+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.00674","created_at":"2026-07-05T03:41:41.695470+00:00"},{"alias_kind":"pith_short_12","alias_value":"NDFL6E6SP63E","created_at":"2026-07-05T03:41:41.695470+00:00"},{"alias_kind":"pith_short_16","alias_value":"NDFL6E6SP63E5WVV","created_at":"2026-07-05T03:41:41.695470+00:00"},{"alias_kind":"pith_short_8","alias_value":"NDFL6E6S","created_at":"2026-07-05T03:41:41.695470+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/NDFL6E6SP63E5WVVFO2SYOVWUV","json":"https://pith.science/pith/NDFL6E6SP63E5WVVFO2SYOVWUV.json","graph_json":"https://pith.science/api/pith-number/NDFL6E6SP63E5WVVFO2SYOVWUV/graph.json","events_json":"https://pith.science/api/pith-number/NDFL6E6SP63E5WVVFO2SYOVWUV/events.json","paper":"https://pith.science/paper/NDFL6E6S"},"agent_actions":{"view_html":"https://pith.science/pith/NDFL6E6SP63E5WVVFO2SYOVWUV","download_json":"https://pith.science/pith/NDFL6E6SP63E5WVVFO2SYOVWUV.json","view_paper":"https://pith.science/paper/NDFL6E6S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.00674&json=true","fetch_graph":"https://pith.science/api/pith-number/NDFL6E6SP63E5WVVFO2SYOVWUV/graph.json","fetch_events":"https://pith.science/api/pith-number/NDFL6E6SP63E5WVVFO2SYOVWUV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NDFL6E6SP63E5WVVFO2SYOVWUV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NDFL6E6SP63E5WVVFO2SYOVWUV/action/storage_attestation","attest_author":"https://pith.science/pith/NDFL6E6SP63E5WVVFO2SYOVWUV/action/author_attestation","sign_citation":"https://pith.science/pith/NDFL6E6SP63E5WVVFO2SYOVWUV/action/citation_signature","submit_replication":"https://pith.science/pith/NDFL6E6SP63E5WVVFO2SYOVWUV/action/replication_record"}},"created_at":"2026-07-05T03:41:41.695470+00:00","updated_at":"2026-07-05T03:41:41.695470+00:00"}