{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:AX2K4ZNUNI4YZTJRH74DMDNEWW","short_pith_number":"pith:AX2K4ZNU","schema_version":"1.0","canonical_sha256":"05f4ae65b46a398ccd313ff8360da4b5abf59ac74602308fc6fb96e4771a3e04","source":{"kind":"arxiv","id":"1704.08545","version":2},"attestation_state":"computed","paper":{"title":"ICNet for Real-Time Semantic Segmentation on High-Resolution Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hengshuang Zhao, Jianping Shi, Jiaya Jia, Xiaojuan Qi, Xiaoyong Shen","submitted_at":"2017-04-27T13:02:49Z","abstract_excerpt":"We focus on the challenging task of real-time semantic segmentation in this paper. It finds many practical applications and yet is with fundamental difficulty of reducing a large portion of computation for pixel-wise label inference. We propose an image cascade network (ICNet) that incorporates multi-resolution branches under proper label guidance to address this challenge. We provide in-depth analysis of our framework and introduce the cascade feature fusion unit to quickly achieve high-quality segmentation. Our system yields real-time inference on a single GPU card with decent quality result"},"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":"1704.08545","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-27T13:02:49Z","cross_cats_sorted":[],"title_canon_sha256":"bcc76766bf4f190ac90b2add1ec1ed7b93951299203fb5e06fefffade084e70e","abstract_canon_sha256":"c0f218375300175ee917ecf23ed336480773aff87dd9dc0daf1645f5de5e18c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:50.864983Z","signature_b64":"yMHcAZK5DoksB0QM+TVs0A2LCz/noFeqGxYAceQ4S+rFajTp1QW0FeeEhJo9vVGyJ37TtKAnqnZ1ju0a+B9SDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05f4ae65b46a398ccd313ff8360da4b5abf59ac74602308fc6fb96e4771a3e04","last_reissued_at":"2026-05-18T00:07:50.864277Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:50.864277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ICNet for Real-Time Semantic Segmentation on High-Resolution Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hengshuang Zhao, Jianping Shi, Jiaya Jia, Xiaojuan Qi, Xiaoyong Shen","submitted_at":"2017-04-27T13:02:49Z","abstract_excerpt":"We focus on the challenging task of real-time semantic segmentation in this paper. It finds many practical applications and yet is with fundamental difficulty of reducing a large portion of computation for pixel-wise label inference. We propose an image cascade network (ICNet) that incorporates multi-resolution branches under proper label guidance to address this challenge. We provide in-depth analysis of our framework and introduce the cascade feature fusion unit to quickly achieve high-quality segmentation. Our system yields real-time inference on a single GPU card with decent quality result"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.08545","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":""},"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":"1704.08545","created_at":"2026-05-18T00:07:50.864413+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.08545v2","created_at":"2026-05-18T00:07:50.864413+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.08545","created_at":"2026-05-18T00:07:50.864413+00:00"},{"alias_kind":"pith_short_12","alias_value":"AX2K4ZNUNI4Y","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"AX2K4ZNUNI4YZTJR","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"AX2K4ZNU","created_at":"2026-05-18T12:31:08.081275+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1906.09826","citing_title":"ESNet: An Efficient Symmetric Network for Real-time Semantic Segmentation","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"1907.06876","citing_title":"Separable Convolutional LSTMs for Faster Video Segmentation","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"1907.07156","citing_title":"Efficient Segmentation: Learning Downsampling Near Semantic Boundaries","ref_index":56,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AX2K4ZNUNI4YZTJRH74DMDNEWW","json":"https://pith.science/pith/AX2K4ZNUNI4YZTJRH74DMDNEWW.json","graph_json":"https://pith.science/api/pith-number/AX2K4ZNUNI4YZTJRH74DMDNEWW/graph.json","events_json":"https://pith.science/api/pith-number/AX2K4ZNUNI4YZTJRH74DMDNEWW/events.json","paper":"https://pith.science/paper/AX2K4ZNU"},"agent_actions":{"view_html":"https://pith.science/pith/AX2K4ZNUNI4YZTJRH74DMDNEWW","download_json":"https://pith.science/pith/AX2K4ZNUNI4YZTJRH74DMDNEWW.json","view_paper":"https://pith.science/paper/AX2K4ZNU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.08545&json=true","fetch_graph":"https://pith.science/api/pith-number/AX2K4ZNUNI4YZTJRH74DMDNEWW/graph.json","fetch_events":"https://pith.science/api/pith-number/AX2K4ZNUNI4YZTJRH74DMDNEWW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AX2K4ZNUNI4YZTJRH74DMDNEWW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AX2K4ZNUNI4YZTJRH74DMDNEWW/action/storage_attestation","attest_author":"https://pith.science/pith/AX2K4ZNUNI4YZTJRH74DMDNEWW/action/author_attestation","sign_citation":"https://pith.science/pith/AX2K4ZNUNI4YZTJRH74DMDNEWW/action/citation_signature","submit_replication":"https://pith.science/pith/AX2K4ZNUNI4YZTJRH74DMDNEWW/action/replication_record"}},"created_at":"2026-05-18T00:07:50.864413+00:00","updated_at":"2026-05-18T00:07:50.864413+00:00"}