{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:2C7GWS3WBHJFSY4PUR3Y3X6VXD","short_pith_number":"pith:2C7GWS3W","schema_version":"1.0","canonical_sha256":"d0be6b4b7609d259638fa4778ddfd5b8fe4becdfc496bff3a81f11a19ff3e04a","source":{"kind":"arxiv","id":"1511.07122","version":3},"attestation_state":"computed","paper":{"title":"Multi-Scale Context Aggregation by Dilated Convolutions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fisher Yu, Vladlen Koltun","submitted_at":"2015-11-23T07:32:14Z","abstract_excerpt":"State-of-the-art models for semantic segmentation are based on adaptations of convolutional networks that had originally been designed for image classification. However, dense prediction and image classification are structurally different. In this work, we develop a new convolutional network module that is specifically designed for dense prediction. The presented module uses dilated convolutions to systematically aggregate multi-scale contextual information without losing resolution. The architecture is based on the fact that dilated convolutions support exponential expansion of the receptive "},"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":"1511.07122","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-11-23T07:32:14Z","cross_cats_sorted":[],"title_canon_sha256":"bc30b0f5db1fd2c244cd7ec7d15334781448b6e1a88a1d5af93ff6e85d7f466b","abstract_canon_sha256":"750d99545e3af650f3fc6aada44c778a141dde6ae9d4e60da09e027203a8e96c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:15:57.911597Z","signature_b64":"wGCMTcGL9l9Y5L7SilY7Co65i3pi65dypTp4NbeuG/xmR/LMf4Nu8kLGhWNyOiGwjk2e1zgSiJJPs6/tObpoCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0be6b4b7609d259638fa4778ddfd5b8fe4becdfc496bff3a81f11a19ff3e04a","last_reissued_at":"2026-05-18T01:15:57.910940Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:15:57.910940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Scale Context Aggregation by Dilated Convolutions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fisher Yu, Vladlen Koltun","submitted_at":"2015-11-23T07:32:14Z","abstract_excerpt":"State-of-the-art models for semantic segmentation are based on adaptations of convolutional networks that had originally been designed for image classification. However, dense prediction and image classification are structurally different. In this work, we develop a new convolutional network module that is specifically designed for dense prediction. The presented module uses dilated convolutions to systematically aggregate multi-scale contextual information without losing resolution. The architecture is based on the fact that dilated convolutions support exponential expansion of the receptive "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.07122","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":"1511.07122","created_at":"2026-05-18T01:15:57.911054+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.07122v3","created_at":"2026-05-18T01:15:57.911054+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.07122","created_at":"2026-05-18T01:15:57.911054+00:00"},{"alias_kind":"pith_short_12","alias_value":"2C7GWS3WBHJF","created_at":"2026-05-18T12:28:59.999130+00:00"},{"alias_kind":"pith_short_16","alias_value":"2C7GWS3WBHJFSY4P","created_at":"2026-05-18T12:28:59.999130+00:00"},{"alias_kind":"pith_short_8","alias_value":"2C7GWS3W","created_at":"2026-05-18T12:28:59.999130+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":32,"internal_anchor_count":19,"sample":[{"citing_arxiv_id":"1906.09354","citing_title":"Boosting the rule-out accuracy of deep disease detection using class weight modifiers","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"1906.09826","citing_title":"ESNet: An Efficient Symmetric Network for Real-time Semantic Segmentation","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"1906.11171","citing_title":"Modeling Embedding Dimension Correlations via Convolutional Neural Collaborative Filtering","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"1907.00887","citing_title":"An Efficient Solution for Breast Tumor Segmentation and Classification in Ultrasound Images Using Deep Adversarial Learning","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"1907.01342","citing_title":"The Ethical Dilemma when (not) Setting up Cost-based Decision Rules in Semantic Segmentation","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"1907.03050","citing_title":"Jointly Aligning and Predicting Continuous Emotion Annotations","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"1907.03241","citing_title":"ASCNet: Adaptive-Scale Convolutional Neural Networks for Multi-Scale Feature Learning","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"1907.03128","citing_title":"Multi-level Wavelet Convolutional Neural Networks","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"1907.03958","citing_title":"Attentive CT Lesion Detection Using Deep Pyramid Inference with Multi-Scale Booster","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"1907.06119","citing_title":"Understanding Deep Learning Techniques for Image Segmentation","ref_index":211,"is_internal_anchor":true},{"citing_arxiv_id":"1907.06968","citing_title":"A Unified Deep Framework for Joint 3D Pose Estimation and Action Recognition from a Single RGB Camera","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"1907.07011","citing_title":"Improving Semantic Segmentation via Dilated Affinity","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"1907.07156","citing_title":"Efficient Segmentation: Learning Downsampling Near Semantic Boundaries","ref_index":55,"is_internal_anchor":true},{"citing_arxiv_id":"1907.08427","citing_title":"VRSTC: Occlusion-Free Video Person Re-Identification","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"1907.10958","citing_title":"Cross Attention Network for Semantic Segmentation","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"1907.11475","citing_title":"Single Level Feature-to-Feature Forecasting with Deformable Convolutions","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2408.12406","citing_title":"Generalized SAM: Efficient Fine-Tuning of SAM for Variable Input Image Sizes","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20760","citing_title":"SpineContextResUNet: A Computationally Efficient Residual UNet for Spine CT Segmentation","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13621","citing_title":"WD-FQDet: Multispectral Detection Transformer via Wavelet Decomposition and Frequency-aware Query Learning","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02670","citing_title":"Cross-subject Muscle Fatigue Detection via Adversarial and Supervised Contrastive Learning with Inception-Attention Network","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12046","citing_title":"Rethink the Role of Neural Decoders in Quantum Error Correction","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"1609.03499","citing_title":"WaveNet: A Generative Model for Raw Audio","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26893","citing_title":"Graph-based Semantic Calibration Network for Unaligned UAV RGBT Image Semantic Segmentation and A Large-scale Benchmark","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"1605.08803","citing_title":"Density estimation using Real NVP","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25188","citing_title":"Image Classification via Random Dilated Convolution with Multi-Branch Feature Extraction and Context Excitation","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2C7GWS3WBHJFSY4PUR3Y3X6VXD","json":"https://pith.science/pith/2C7GWS3WBHJFSY4PUR3Y3X6VXD.json","graph_json":"https://pith.science/api/pith-number/2C7GWS3WBHJFSY4PUR3Y3X6VXD/graph.json","events_json":"https://pith.science/api/pith-number/2C7GWS3WBHJFSY4PUR3Y3X6VXD/events.json","paper":"https://pith.science/paper/2C7GWS3W"},"agent_actions":{"view_html":"https://pith.science/pith/2C7GWS3WBHJFSY4PUR3Y3X6VXD","download_json":"https://pith.science/pith/2C7GWS3WBHJFSY4PUR3Y3X6VXD.json","view_paper":"https://pith.science/paper/2C7GWS3W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.07122&json=true","fetch_graph":"https://pith.science/api/pith-number/2C7GWS3WBHJFSY4PUR3Y3X6VXD/graph.json","fetch_events":"https://pith.science/api/pith-number/2C7GWS3WBHJFSY4PUR3Y3X6VXD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2C7GWS3WBHJFSY4PUR3Y3X6VXD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2C7GWS3WBHJFSY4PUR3Y3X6VXD/action/storage_attestation","attest_author":"https://pith.science/pith/2C7GWS3WBHJFSY4PUR3Y3X6VXD/action/author_attestation","sign_citation":"https://pith.science/pith/2C7GWS3WBHJFSY4PUR3Y3X6VXD/action/citation_signature","submit_replication":"https://pith.science/pith/2C7GWS3WBHJFSY4PUR3Y3X6VXD/action/replication_record"}},"created_at":"2026-05-18T01:15:57.911054+00:00","updated_at":"2026-05-18T01:15:57.911054+00:00"}