{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ORGPSERXR4V2SRB2BZ3V5BQ46Z","short_pith_number":"pith:ORGPSERX","schema_version":"1.0","canonical_sha256":"744cf912378f2ba9443a0e775e861cf6710e934f371c092d959048d2f11b94a7","source":{"kind":"arxiv","id":"1802.02611","version":3},"attestation_state":"computed","paper":{"title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Florian Schroff, George Papandreou, Hartwig Adam, Liang-Chieh Chen, Yukun Zhu","submitted_at":"2018-02-07T19:37:11Z","abstract_excerpt":"Spatial pyramid pooling module or encode-decoder structure are used in deep neural networks for semantic segmentation task. The former networks are able to encode multi-scale contextual information by probing the incoming features with filters or pooling operations at multiple rates and multiple effective fields-of-view, while the latter networks can capture sharper object boundaries by gradually recovering the spatial information. In this work, we propose to combine the advantages from both methods. Specifically, our proposed model, DeepLabv3+, extends DeepLabv3 by adding a simple yet effecti"},"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":"1802.02611","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-07T19:37:11Z","cross_cats_sorted":[],"title_canon_sha256":"7dc48fd705e03ce2c75513c98f6489054b0bef6b92474be2ebe242ae81576eb4","abstract_canon_sha256":"bfab8f11779f44a1a3911428c5285a9b3eb888a759f125375b1c0d8e7ea63f86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:27.952851Z","signature_b64":"BkehIK6YSFKYfDppxzNvVbE16ZT9HvtbE6GlklJUlLnNHepDfU2dhnhrKxNc3VlLskH+Q5KmGVFM0YkEAaNjAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"744cf912378f2ba9443a0e775e861cf6710e934f371c092d959048d2f11b94a7","last_reissued_at":"2026-05-18T00:07:27.952155Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:27.952155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Florian Schroff, George Papandreou, Hartwig Adam, Liang-Chieh Chen, Yukun Zhu","submitted_at":"2018-02-07T19:37:11Z","abstract_excerpt":"Spatial pyramid pooling module or encode-decoder structure are used in deep neural networks for semantic segmentation task. The former networks are able to encode multi-scale contextual information by probing the incoming features with filters or pooling operations at multiple rates and multiple effective fields-of-view, while the latter networks can capture sharper object boundaries by gradually recovering the spatial information. In this work, we propose to combine the advantages from both methods. Specifically, our proposed model, DeepLabv3+, extends DeepLabv3 by adding a simple yet effecti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.02611","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":"1802.02611","created_at":"2026-05-18T00:07:27.952255+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.02611v3","created_at":"2026-05-18T00:07:27.952255+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.02611","created_at":"2026-05-18T00:07:27.952255+00:00"},{"alias_kind":"pith_short_12","alias_value":"ORGPSERXR4V2","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"ORGPSERXR4V2SRB2","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"ORGPSERX","created_at":"2026-05-18T12:32:43.782077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":10,"sample":[{"citing_arxiv_id":"1907.01342","citing_title":"The Ethical Dilemma when (not) Setting up Cost-based Decision Rules in Semantic Segmentation","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"1907.03089","citing_title":"SAN: Scale-Aware Network for Semantic Segmentation of High-Resolution Aerial Images","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"1907.06119","citing_title":"Understanding Deep Learning Techniques for Image Segmentation","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"1907.07011","citing_title":"Improving Semantic Segmentation via Dilated Affinity","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"1907.09905","citing_title":"U4D: Unsupervised 4D Dynamic Scene Understanding","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20276","citing_title":"OmniISR: A Unified Framework for Centralized and Federated Learning via Intermediate Supervision and Regularization","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17630","citing_title":"SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17630","citing_title":"SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2512.06949","citing_title":"Can We Go Beyond Visual Features? Neural Tissue Relation Modeling for Relational Graph Analysis in Non-Melanoma Skin Histology","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2602.05880","citing_title":"Contour Refinement using Discrete Diffusion in Low Data Regime","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23776","citing_title":"From Noisy Historical Maps to Time-Series Oil Palm Mapping Without Annotation in Malaysia and Indonesia (2020-2024)","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00367","citing_title":"Flow matching for Sentinel-2 super-resolution: implementation, application, and implications","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07370","citing_title":"MORPH-U: Multi-Objective Resilient Motion Planning for V2X-Enabled Autonomous Driving in High-Uncertainty Environments via Simulation","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ORGPSERXR4V2SRB2BZ3V5BQ46Z","json":"https://pith.science/pith/ORGPSERXR4V2SRB2BZ3V5BQ46Z.json","graph_json":"https://pith.science/api/pith-number/ORGPSERXR4V2SRB2BZ3V5BQ46Z/graph.json","events_json":"https://pith.science/api/pith-number/ORGPSERXR4V2SRB2BZ3V5BQ46Z/events.json","paper":"https://pith.science/paper/ORGPSERX"},"agent_actions":{"view_html":"https://pith.science/pith/ORGPSERXR4V2SRB2BZ3V5BQ46Z","download_json":"https://pith.science/pith/ORGPSERXR4V2SRB2BZ3V5BQ46Z.json","view_paper":"https://pith.science/paper/ORGPSERX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.02611&json=true","fetch_graph":"https://pith.science/api/pith-number/ORGPSERXR4V2SRB2BZ3V5BQ46Z/graph.json","fetch_events":"https://pith.science/api/pith-number/ORGPSERXR4V2SRB2BZ3V5BQ46Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ORGPSERXR4V2SRB2BZ3V5BQ46Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ORGPSERXR4V2SRB2BZ3V5BQ46Z/action/storage_attestation","attest_author":"https://pith.science/pith/ORGPSERXR4V2SRB2BZ3V5BQ46Z/action/author_attestation","sign_citation":"https://pith.science/pith/ORGPSERXR4V2SRB2BZ3V5BQ46Z/action/citation_signature","submit_replication":"https://pith.science/pith/ORGPSERXR4V2SRB2BZ3V5BQ46Z/action/replication_record"}},"created_at":"2026-05-18T00:07:27.952255+00:00","updated_at":"2026-05-18T00:07:27.952255+00:00"}