{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:F4ZX5Y46KERJZUQVGCTZ4HWV42","short_pith_number":"pith:F4ZX5Y46","schema_version":"1.0","canonical_sha256":"2f337ee39e51229cd21530a79e1ed5e69560e2beea02ca549411283df8d4d8d5","source":{"kind":"arxiv","id":"2308.04243","version":1},"attestation_state":"computed","paper":{"title":"AICSD: Adaptive Inter-Class Similarity Distillation for Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amir M. Mansourian, Rozhan Ahmadi, Shohreh Kasaei","submitted_at":"2023-08-08T13:17:20Z","abstract_excerpt":"In recent years, deep neural networks have achieved remarkable accuracy in computer vision tasks. With inference time being a crucial factor, particularly in dense prediction tasks such as semantic segmentation, knowledge distillation has emerged as a successful technique for improving the accuracy of lightweight student networks. The existing methods often neglect the information in channels and among different classes. To overcome these limitations, this paper proposes a novel method called Inter-Class Similarity Distillation (ICSD) for the purpose of knowledge distillation. The proposed met"},"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":"2308.04243","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-08T13:17:20Z","cross_cats_sorted":[],"title_canon_sha256":"cf4bffc040d2db7642312483d484c1d6a9f20eda2e84a2980bc3c66dc700dcbb","abstract_canon_sha256":"418784bd9a9f5a7314480dd287130ce8ff2998e49add309269ecfc774ad118c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:39:24.549557Z","signature_b64":"y/Y1B/9Hx6o32hciiE4budoVCwcjK0Cbs5wj+AS8dq9qukfeD2IJKUd1ye+P/+ho3EaAPae3z/IGjjZyyzjADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f337ee39e51229cd21530a79e1ed5e69560e2beea02ca549411283df8d4d8d5","last_reissued_at":"2026-07-05T06:39:24.548932Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:39:24.548932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AICSD: Adaptive Inter-Class Similarity Distillation for Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amir M. Mansourian, Rozhan Ahmadi, Shohreh Kasaei","submitted_at":"2023-08-08T13:17:20Z","abstract_excerpt":"In recent years, deep neural networks have achieved remarkable accuracy in computer vision tasks. With inference time being a crucial factor, particularly in dense prediction tasks such as semantic segmentation, knowledge distillation has emerged as a successful technique for improving the accuracy of lightweight student networks. The existing methods often neglect the information in channels and among different classes. To overcome these limitations, this paper proposes a novel method called Inter-Class Similarity Distillation (ICSD) for the purpose of knowledge distillation. The proposed met"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.04243","kind":"arxiv","version":1},"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/2308.04243/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":"2308.04243","created_at":"2026-07-05T06:39:24.548990+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.04243v1","created_at":"2026-07-05T06:39:24.548990+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.04243","created_at":"2026-07-05T06:39:24.548990+00:00"},{"alias_kind":"pith_short_12","alias_value":"F4ZX5Y46KERJ","created_at":"2026-07-05T06:39:24.548990+00:00"},{"alias_kind":"pith_short_16","alias_value":"F4ZX5Y46KERJZUQV","created_at":"2026-07-05T06:39:24.548990+00:00"},{"alias_kind":"pith_short_8","alias_value":"F4ZX5Y46","created_at":"2026-07-05T06:39:24.548990+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30577","citing_title":"APRIL-MedSeg: A Modular Medical Image Segmentation Toolbox Embracing Modern Paradigms","ref_index":279,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30577","citing_title":"APRIL-MedSeg: A Modular Medical Image Segmentation Toolbox Embracing Modern Paradigms","ref_index":163,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F4ZX5Y46KERJZUQVGCTZ4HWV42","json":"https://pith.science/pith/F4ZX5Y46KERJZUQVGCTZ4HWV42.json","graph_json":"https://pith.science/api/pith-number/F4ZX5Y46KERJZUQVGCTZ4HWV42/graph.json","events_json":"https://pith.science/api/pith-number/F4ZX5Y46KERJZUQVGCTZ4HWV42/events.json","paper":"https://pith.science/paper/F4ZX5Y46"},"agent_actions":{"view_html":"https://pith.science/pith/F4ZX5Y46KERJZUQVGCTZ4HWV42","download_json":"https://pith.science/pith/F4ZX5Y46KERJZUQVGCTZ4HWV42.json","view_paper":"https://pith.science/paper/F4ZX5Y46","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.04243&json=true","fetch_graph":"https://pith.science/api/pith-number/F4ZX5Y46KERJZUQVGCTZ4HWV42/graph.json","fetch_events":"https://pith.science/api/pith-number/F4ZX5Y46KERJZUQVGCTZ4HWV42/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F4ZX5Y46KERJZUQVGCTZ4HWV42/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F4ZX5Y46KERJZUQVGCTZ4HWV42/action/storage_attestation","attest_author":"https://pith.science/pith/F4ZX5Y46KERJZUQVGCTZ4HWV42/action/author_attestation","sign_citation":"https://pith.science/pith/F4ZX5Y46KERJZUQVGCTZ4HWV42/action/citation_signature","submit_replication":"https://pith.science/pith/F4ZX5Y46KERJZUQVGCTZ4HWV42/action/replication_record"}},"created_at":"2026-07-05T06:39:24.548990+00:00","updated_at":"2026-07-05T06:39:24.548990+00:00"}