{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:SJJL6QBHKDW577HLTR2B3NPOSV","short_pith_number":"pith:SJJL6QBH","schema_version":"1.0","canonical_sha256":"9252bf402750eddffceb9c741db5ee95647dc0c556e2844a77b5a287beb2367a","source":{"kind":"arxiv","id":"1803.06815","version":3},"attestation_state":"computed","paper":{"title":"ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anat Caspi, Hannaneh Hajishirzi, Linda Shapiro, Mohammad Rastegari, Sachin Mehta","submitted_at":"2018-03-19T06:42:47Z","abstract_excerpt":"We introduce a fast and efficient convolutional neural network, ESPNet, for semantic segmentation of high resolution images under resource constraints. ESPNet is based on a new convolutional module, efficient spatial pyramid (ESP), which is efficient in terms of computation, memory, and power. ESPNet is 22 times faster (on a standard GPU) and 180 times smaller than the state-of-the-art semantic segmentation network PSPNet, while its category-wise accuracy is only 8% less. We evaluated ESPNet on a variety of semantic segmentation datasets including Cityscapes, PASCAL VOC, and a breast biopsy wh"},"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":"1803.06815","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-19T06:42:47Z","cross_cats_sorted":[],"title_canon_sha256":"d938134f75bbfbf65a9263901936ee3368a78f9e20a7732c439cff1643c53419","abstract_canon_sha256":"c7bcbb06ddc22271434e9a7248800250b988bbb5dc2064bfdf15c305f37a910b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:52.506128Z","signature_b64":"qGd/Vz2xPkY2a2deYnH+7R/ukAoC0ANhDa/YMDtN7KE8DMC/+WnUn6OcqHlkBbXjDNUPd2z8XAVvwm6Bl7LmDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9252bf402750eddffceb9c741db5ee95647dc0c556e2844a77b5a287beb2367a","last_reissued_at":"2026-05-18T00:09:52.505609Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:52.505609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anat Caspi, Hannaneh Hajishirzi, Linda Shapiro, Mohammad Rastegari, Sachin Mehta","submitted_at":"2018-03-19T06:42:47Z","abstract_excerpt":"We introduce a fast and efficient convolutional neural network, ESPNet, for semantic segmentation of high resolution images under resource constraints. ESPNet is based on a new convolutional module, efficient spatial pyramid (ESP), which is efficient in terms of computation, memory, and power. ESPNet is 22 times faster (on a standard GPU) and 180 times smaller than the state-of-the-art semantic segmentation network PSPNet, while its category-wise accuracy is only 8% less. We evaluated ESPNet on a variety of semantic segmentation datasets including Cityscapes, PASCAL VOC, and a breast biopsy wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.06815","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":""},"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":"1803.06815","created_at":"2026-05-18T00:09:52.505696+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.06815v3","created_at":"2026-05-18T00:09:52.505696+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.06815","created_at":"2026-05-18T00:09:52.505696+00:00"},{"alias_kind":"pith_short_12","alias_value":"SJJL6QBHKDW5","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"SJJL6QBHKDW577HL","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"SJJL6QBH","created_at":"2026-05-18T12:32:53.628368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.09826","citing_title":"ESNet: An Efficient Symmetric Network for Real-time Semantic Segmentation","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SJJL6QBHKDW577HLTR2B3NPOSV","json":"https://pith.science/pith/SJJL6QBHKDW577HLTR2B3NPOSV.json","graph_json":"https://pith.science/api/pith-number/SJJL6QBHKDW577HLTR2B3NPOSV/graph.json","events_json":"https://pith.science/api/pith-number/SJJL6QBHKDW577HLTR2B3NPOSV/events.json","paper":"https://pith.science/paper/SJJL6QBH"},"agent_actions":{"view_html":"https://pith.science/pith/SJJL6QBHKDW577HLTR2B3NPOSV","download_json":"https://pith.science/pith/SJJL6QBHKDW577HLTR2B3NPOSV.json","view_paper":"https://pith.science/paper/SJJL6QBH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.06815&json=true","fetch_graph":"https://pith.science/api/pith-number/SJJL6QBHKDW577HLTR2B3NPOSV/graph.json","fetch_events":"https://pith.science/api/pith-number/SJJL6QBHKDW577HLTR2B3NPOSV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SJJL6QBHKDW577HLTR2B3NPOSV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SJJL6QBHKDW577HLTR2B3NPOSV/action/storage_attestation","attest_author":"https://pith.science/pith/SJJL6QBHKDW577HLTR2B3NPOSV/action/author_attestation","sign_citation":"https://pith.science/pith/SJJL6QBHKDW577HLTR2B3NPOSV/action/citation_signature","submit_replication":"https://pith.science/pith/SJJL6QBHKDW577HLTR2B3NPOSV/action/replication_record"}},"created_at":"2026-05-18T00:09:52.505696+00:00","updated_at":"2026-05-18T00:09:52.505696+00:00"}