{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:74GDWXSXFJ6K4RVQQEEDBOSYMU","short_pith_number":"pith:74GDWXSX","schema_version":"1.0","canonical_sha256":"ff0c3b5e572a7cae46b0810830ba58653da21ee9eebb06a3e2bf3eb97e1b2b09","source":{"kind":"arxiv","id":"2305.03944","version":3},"attestation_state":"computed","paper":{"title":"Structural and Statistical Texture Knowledge Distillation for Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deyi Ji, Haoran Wang, Hongtao Lu, Jianqiang Huang, Mingyuan Tao, Xian-Sheng Hua","submitted_at":"2023-05-06T06:01:11Z","abstract_excerpt":"Existing knowledge distillation works for semantic segmentation mainly focus on transferring high-level contextual knowledge from teacher to student. However, low-level texture knowledge is also of vital importance for characterizing the local structural pattern and global statistical property, such as boundary, smoothness, regularity and color contrast, which may not be well addressed by high-level deep features. In this paper, we are intended to take full advantage of both structural and statistical texture knowledge and propose a novel Structural and Statistical Texture Knowledge Distillati"},"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":"2305.03944","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-06T06:01:11Z","cross_cats_sorted":[],"title_canon_sha256":"4426814e004133435152deaffc86152d9e15f381868ae2984aadc1abdd0554ac","abstract_canon_sha256":"579771d1cf8b0588c7666c3ba8cf761896c579de1dfc8e68d186e62729757979"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:38.936581Z","signature_b64":"OqTjc82hWWumhA6T66ZMA+Umcff2Wul+hdmZzIeNxCP3E/zv6Tu22eT2AORphJbaKRszK9QP4jP+vuv8morBCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff0c3b5e572a7cae46b0810830ba58653da21ee9eebb06a3e2bf3eb97e1b2b09","last_reissued_at":"2026-07-05T10:31:38.936064Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:38.936064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structural and Statistical Texture Knowledge Distillation for Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deyi Ji, Haoran Wang, Hongtao Lu, Jianqiang Huang, Mingyuan Tao, Xian-Sheng Hua","submitted_at":"2023-05-06T06:01:11Z","abstract_excerpt":"Existing knowledge distillation works for semantic segmentation mainly focus on transferring high-level contextual knowledge from teacher to student. However, low-level texture knowledge is also of vital importance for characterizing the local structural pattern and global statistical property, such as boundary, smoothness, regularity and color contrast, which may not be well addressed by high-level deep features. In this paper, we are intended to take full advantage of both structural and statistical texture knowledge and propose a novel Structural and Statistical Texture Knowledge Distillati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03944","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2305.03944/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":"2305.03944","created_at":"2026-07-05T10:31:38.936124+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.03944v3","created_at":"2026-07-05T10:31:38.936124+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03944","created_at":"2026-07-05T10:31:38.936124+00:00"},{"alias_kind":"pith_short_12","alias_value":"74GDWXSXFJ6K","created_at":"2026-07-05T10:31:38.936124+00:00"},{"alias_kind":"pith_short_16","alias_value":"74GDWXSXFJ6K4RVQ","created_at":"2026-07-05T10:31:38.936124+00:00"},{"alias_kind":"pith_short_8","alias_value":"74GDWXSX","created_at":"2026-07-05T10:31:38.936124+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.02753","citing_title":"DeCo-DETR: Decoupled Cognition DETR for efficient Open-Vocabulary Object Detection","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02753","citing_title":"DeCo-DETR: Decoupled Cognition DETR for efficient Open-Vocabulary Object Detection","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/74GDWXSXFJ6K4RVQQEEDBOSYMU","json":"https://pith.science/pith/74GDWXSXFJ6K4RVQQEEDBOSYMU.json","graph_json":"https://pith.science/api/pith-number/74GDWXSXFJ6K4RVQQEEDBOSYMU/graph.json","events_json":"https://pith.science/api/pith-number/74GDWXSXFJ6K4RVQQEEDBOSYMU/events.json","paper":"https://pith.science/paper/74GDWXSX"},"agent_actions":{"view_html":"https://pith.science/pith/74GDWXSXFJ6K4RVQQEEDBOSYMU","download_json":"https://pith.science/pith/74GDWXSXFJ6K4RVQQEEDBOSYMU.json","view_paper":"https://pith.science/paper/74GDWXSX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.03944&json=true","fetch_graph":"https://pith.science/api/pith-number/74GDWXSXFJ6K4RVQQEEDBOSYMU/graph.json","fetch_events":"https://pith.science/api/pith-number/74GDWXSXFJ6K4RVQQEEDBOSYMU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/74GDWXSXFJ6K4RVQQEEDBOSYMU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/74GDWXSXFJ6K4RVQQEEDBOSYMU/action/storage_attestation","attest_author":"https://pith.science/pith/74GDWXSXFJ6K4RVQQEEDBOSYMU/action/author_attestation","sign_citation":"https://pith.science/pith/74GDWXSXFJ6K4RVQQEEDBOSYMU/action/citation_signature","submit_replication":"https://pith.science/pith/74GDWXSXFJ6K4RVQQEEDBOSYMU/action/replication_record"}},"created_at":"2026-07-05T10:31:38.936124+00:00","updated_at":"2026-07-05T10:31:38.936124+00:00"}