{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:L7TOTASXCSHT5UXAQEJG4VELPB","short_pith_number":"pith:L7TOTASX","schema_version":"1.0","canonical_sha256":"5fe6e98257148f3ed2e081126e548b785000182c817ef9e33fc39aedf88274ae","source":{"kind":"arxiv","id":"1703.02719","version":1},"attestation_state":"computed","paper":{"title":"Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Peng, Gang Yu, Guiming Luo, Jian Sun, Xiangyu Zhang","submitted_at":"2017-03-08T06:14:55Z","abstract_excerpt":"One of recent trends [30, 31, 14] in network architec- ture design is stacking small filters (e.g., 1x1 or 3x3) in the entire network because the stacked small filters is more ef- ficient than a large kernel, given the same computational complexity. However, in the field of semantic segmenta- tion, where we need to perform dense per-pixel prediction, we find that the large kernel (and effective receptive field) plays an important role when we have to perform the clas- sification and localization tasks simultaneously. Following our design principle, we propose a Global Convolutional Network to "},"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":"1703.02719","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-08T06:14:55Z","cross_cats_sorted":[],"title_canon_sha256":"01e8d834e7cdb785a342e51a8e7e8d4bea3ec24369d4450daa5b0ffbd9c3721c","abstract_canon_sha256":"77565e73021f20b2aeb97d711f2487fc227f6ea4b6e724862a394c79b76e7e70"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:05.795283Z","signature_b64":"GXOtoSYBKVge3t7GzDQXw8eLTSM+2ke4nrLWwhFH3cg2vHhjbO1WPibh6o9kMlwwc5ONL8rJsMmTXnc0p15KBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fe6e98257148f3ed2e081126e548b785000182c817ef9e33fc39aedf88274ae","last_reissued_at":"2026-05-18T00:49:05.794755Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:05.794755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Peng, Gang Yu, Guiming Luo, Jian Sun, Xiangyu Zhang","submitted_at":"2017-03-08T06:14:55Z","abstract_excerpt":"One of recent trends [30, 31, 14] in network architec- ture design is stacking small filters (e.g., 1x1 or 3x3) in the entire network because the stacked small filters is more ef- ficient than a large kernel, given the same computational complexity. However, in the field of semantic segmenta- tion, where we need to perform dense per-pixel prediction, we find that the large kernel (and effective receptive field) plays an important role when we have to perform the clas- sification and localization tasks simultaneously. Following our design principle, we propose a Global Convolutional Network to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.02719","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":"1703.02719","created_at":"2026-05-18T00:49:05.794833+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.02719v1","created_at":"2026-05-18T00:49:05.794833+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.02719","created_at":"2026-05-18T00:49:05.794833+00:00"},{"alias_kind":"pith_short_12","alias_value":"L7TOTASXCSHT","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"L7TOTASXCSHT5UXA","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"L7TOTASX","created_at":"2026-05-18T12:31:28.150371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1907.03089","citing_title":"SAN: Scale-Aware Network for Semantic Segmentation of High-Resolution Aerial Images","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"1907.06119","citing_title":"Understanding Deep Learning Techniques for Image Segmentation","ref_index":165,"is_internal_anchor":true},{"citing_arxiv_id":"1706.05587","citing_title":"Rethinking Atrous Convolution for Semantic Image Segmentation","ref_index":68,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L7TOTASXCSHT5UXAQEJG4VELPB","json":"https://pith.science/pith/L7TOTASXCSHT5UXAQEJG4VELPB.json","graph_json":"https://pith.science/api/pith-number/L7TOTASXCSHT5UXAQEJG4VELPB/graph.json","events_json":"https://pith.science/api/pith-number/L7TOTASXCSHT5UXAQEJG4VELPB/events.json","paper":"https://pith.science/paper/L7TOTASX"},"agent_actions":{"view_html":"https://pith.science/pith/L7TOTASXCSHT5UXAQEJG4VELPB","download_json":"https://pith.science/pith/L7TOTASXCSHT5UXAQEJG4VELPB.json","view_paper":"https://pith.science/paper/L7TOTASX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.02719&json=true","fetch_graph":"https://pith.science/api/pith-number/L7TOTASXCSHT5UXAQEJG4VELPB/graph.json","fetch_events":"https://pith.science/api/pith-number/L7TOTASXCSHT5UXAQEJG4VELPB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L7TOTASXCSHT5UXAQEJG4VELPB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L7TOTASXCSHT5UXAQEJG4VELPB/action/storage_attestation","attest_author":"https://pith.science/pith/L7TOTASXCSHT5UXAQEJG4VELPB/action/author_attestation","sign_citation":"https://pith.science/pith/L7TOTASXCSHT5UXAQEJG4VELPB/action/citation_signature","submit_replication":"https://pith.science/pith/L7TOTASXCSHT5UXAQEJG4VELPB/action/replication_record"}},"created_at":"2026-05-18T00:49:05.794833+00:00","updated_at":"2026-05-18T00:49:05.794833+00:00"}