{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ECIB7IUXHYNV3DRWAQEG5Y4EZI","short_pith_number":"pith:ECIB7IUX","schema_version":"1.0","canonical_sha256":"20901fa2973e1b5d8e3604086ee384ca09c8dafea4862e356cb86c1ca007a566","source":{"kind":"arxiv","id":"1806.08522","version":1},"attestation_state":"computed","paper":{"title":"Efficient Semantic Segmentation using Gradual Grouping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"C V Jawahar, Girish Varma, Manu Mathew, Nikitha Vallurupalli, Soyeb Nagori, Sriharsha Annamaneni","submitted_at":"2018-06-22T07:11:41Z","abstract_excerpt":"Deep CNNs for semantic segmentation have high memory and run time requirements. Various approaches have been proposed to make CNNs efficient like grouped, shuffled, depth-wise separable convolutions. We study the effectiveness of these techniques on a real-time semantic segmentation architecture like ERFNet for improving run time by over 5X. We apply these techniques to CNN layers partially or fully and evaluate the testing accuracies on Cityscapes dataset. We obtain accuracy vs parameters/FLOPs trade offs, giving accuracy scores for models that can run under specified runtime budgets. We furt"},"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":"1806.08522","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-22T07:11:41Z","cross_cats_sorted":[],"title_canon_sha256":"ca7f525f37d0077391204c6c40fa53fd90aa98dbf5b2d9f41ba6fcc0de0c50ae","abstract_canon_sha256":"9c25b35666011524e3f3c8f5a8ae32f812229c21f164c381783e602c4a34695f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:36.987042Z","signature_b64":"Ty3php52EYCO3KftntMLerc4JZ7abzqdzaPTQ1oGBoe6pO31tVXEPkBoFnN82KpCJRQfEb5RnpYhdvzfyYL1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20901fa2973e1b5d8e3604086ee384ca09c8dafea4862e356cb86c1ca007a566","last_reissued_at":"2026-05-18T00:12:36.986305Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:36.986305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Semantic Segmentation using Gradual Grouping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"C V Jawahar, Girish Varma, Manu Mathew, Nikitha Vallurupalli, Soyeb Nagori, Sriharsha Annamaneni","submitted_at":"2018-06-22T07:11:41Z","abstract_excerpt":"Deep CNNs for semantic segmentation have high memory and run time requirements. Various approaches have been proposed to make CNNs efficient like grouped, shuffled, depth-wise separable convolutions. We study the effectiveness of these techniques on a real-time semantic segmentation architecture like ERFNet for improving run time by over 5X. We apply these techniques to CNN layers partially or fully and evaluate the testing accuracies on Cityscapes dataset. We obtain accuracy vs parameters/FLOPs trade offs, giving accuracy scores for models that can run under specified runtime budgets. We furt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.08522","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":""},"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":"1806.08522","created_at":"2026-05-18T00:12:36.986445+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.08522v1","created_at":"2026-05-18T00:12:36.986445+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.08522","created_at":"2026-05-18T00:12:36.986445+00:00"},{"alias_kind":"pith_short_12","alias_value":"ECIB7IUXHYNV","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"ECIB7IUXHYNV3DRW","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"ECIB7IUX","created_at":"2026-05-18T12:32:22.470017+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/ECIB7IUXHYNV3DRWAQEG5Y4EZI","json":"https://pith.science/pith/ECIB7IUXHYNV3DRWAQEG5Y4EZI.json","graph_json":"https://pith.science/api/pith-number/ECIB7IUXHYNV3DRWAQEG5Y4EZI/graph.json","events_json":"https://pith.science/api/pith-number/ECIB7IUXHYNV3DRWAQEG5Y4EZI/events.json","paper":"https://pith.science/paper/ECIB7IUX"},"agent_actions":{"view_html":"https://pith.science/pith/ECIB7IUXHYNV3DRWAQEG5Y4EZI","download_json":"https://pith.science/pith/ECIB7IUXHYNV3DRWAQEG5Y4EZI.json","view_paper":"https://pith.science/paper/ECIB7IUX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.08522&json=true","fetch_graph":"https://pith.science/api/pith-number/ECIB7IUXHYNV3DRWAQEG5Y4EZI/graph.json","fetch_events":"https://pith.science/api/pith-number/ECIB7IUXHYNV3DRWAQEG5Y4EZI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ECIB7IUXHYNV3DRWAQEG5Y4EZI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ECIB7IUXHYNV3DRWAQEG5Y4EZI/action/storage_attestation","attest_author":"https://pith.science/pith/ECIB7IUXHYNV3DRWAQEG5Y4EZI/action/author_attestation","sign_citation":"https://pith.science/pith/ECIB7IUXHYNV3DRWAQEG5Y4EZI/action/citation_signature","submit_replication":"https://pith.science/pith/ECIB7IUXHYNV3DRWAQEG5Y4EZI/action/replication_record"}},"created_at":"2026-05-18T00:12:36.986445+00:00","updated_at":"2026-05-18T00:12:36.986445+00:00"}