{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LUVYWXBPGZ2MSZQGCHZ73ZBI5Y","short_pith_number":"pith:LUVYWXBP","schema_version":"1.0","canonical_sha256":"5d2b8b5c2f3674c9660611f3fde428ee29d5ab5a8ce1fd62907d85a7043f3650","source":{"kind":"arxiv","id":"2205.03650","version":2},"attestation_state":"computed","paper":{"title":"Distilling Inter-Class Distance for Semantic Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunluan Zhou, Zhengbo Zhang, Zhigang Tu","submitted_at":"2022-05-07T13:13:55Z","abstract_excerpt":"Knowledge distillation is widely adopted in semantic segmentation to reduce the computation cost.The previous knowledge distillation methods for semantic segmentation focus on pixel-wise feature alignment and intra-class feature variation distillation, neglecting to transfer the knowledge of the inter-class distance in the feature space, which is important for semantic segmentation. To address this issue, we propose an Inter-class Distance Distillation (IDD) method to transfer the inter-class distance in the feature space from the teacher network to the student network. Furthermore, semantic s"},"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":"2205.03650","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-07T13:13:55Z","cross_cats_sorted":[],"title_canon_sha256":"8f483168bdd2403e35e8be4c02f499f9bcee42784f2602254be29f447ee73884","abstract_canon_sha256":"26e718e57585a7e7eeafd460e26fd53f1e534561a9f83ef80108250c143af2d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:40:27.237701Z","signature_b64":"H818Irm6OuJFjwod7c3DMO6fAHhpykOgJVa2tpn1qYA8nva836v/jbBXauoZiu/VVL4v/60kkjWmnZkjDGFUDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d2b8b5c2f3674c9660611f3fde428ee29d5ab5a8ce1fd62907d85a7043f3650","last_reissued_at":"2026-07-05T04:40:27.237156Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:40:27.237156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distilling Inter-Class Distance for Semantic Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunluan Zhou, Zhengbo Zhang, Zhigang Tu","submitted_at":"2022-05-07T13:13:55Z","abstract_excerpt":"Knowledge distillation is widely adopted in semantic segmentation to reduce the computation cost.The previous knowledge distillation methods for semantic segmentation focus on pixel-wise feature alignment and intra-class feature variation distillation, neglecting to transfer the knowledge of the inter-class distance in the feature space, which is important for semantic segmentation. To address this issue, we propose an Inter-class Distance Distillation (IDD) method to transfer the inter-class distance in the feature space from the teacher network to the student network. Furthermore, semantic s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.03650","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2205.03650/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":"2205.03650","created_at":"2026-07-05T04:40:27.237216+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.03650v2","created_at":"2026-07-05T04:40:27.237216+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.03650","created_at":"2026-07-05T04:40:27.237216+00:00"},{"alias_kind":"pith_short_12","alias_value":"LUVYWXBPGZ2M","created_at":"2026-07-05T04:40:27.237216+00:00"},{"alias_kind":"pith_short_16","alias_value":"LUVYWXBPGZ2MSZQG","created_at":"2026-07-05T04:40:27.237216+00:00"},{"alias_kind":"pith_short_8","alias_value":"LUVYWXBP","created_at":"2026-07-05T04:40:27.237216+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01911","citing_title":"Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09063","citing_title":"Frequency-Enhanced Diffusion Models: Curriculum-Guided Semantic Alignment for Zero-Shot Skeleton Action Recognition","ref_index":71,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LUVYWXBPGZ2MSZQGCHZ73ZBI5Y","json":"https://pith.science/pith/LUVYWXBPGZ2MSZQGCHZ73ZBI5Y.json","graph_json":"https://pith.science/api/pith-number/LUVYWXBPGZ2MSZQGCHZ73ZBI5Y/graph.json","events_json":"https://pith.science/api/pith-number/LUVYWXBPGZ2MSZQGCHZ73ZBI5Y/events.json","paper":"https://pith.science/paper/LUVYWXBP"},"agent_actions":{"view_html":"https://pith.science/pith/LUVYWXBPGZ2MSZQGCHZ73ZBI5Y","download_json":"https://pith.science/pith/LUVYWXBPGZ2MSZQGCHZ73ZBI5Y.json","view_paper":"https://pith.science/paper/LUVYWXBP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.03650&json=true","fetch_graph":"https://pith.science/api/pith-number/LUVYWXBPGZ2MSZQGCHZ73ZBI5Y/graph.json","fetch_events":"https://pith.science/api/pith-number/LUVYWXBPGZ2MSZQGCHZ73ZBI5Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LUVYWXBPGZ2MSZQGCHZ73ZBI5Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LUVYWXBPGZ2MSZQGCHZ73ZBI5Y/action/storage_attestation","attest_author":"https://pith.science/pith/LUVYWXBPGZ2MSZQGCHZ73ZBI5Y/action/author_attestation","sign_citation":"https://pith.science/pith/LUVYWXBPGZ2MSZQGCHZ73ZBI5Y/action/citation_signature","submit_replication":"https://pith.science/pith/LUVYWXBPGZ2MSZQGCHZ73ZBI5Y/action/replication_record"}},"created_at":"2026-07-05T04:40:27.237216+00:00","updated_at":"2026-07-05T04:40:27.237216+00:00"}