{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:IB6IDYKJALE6O7J6ZVM7OOYNQR","short_pith_number":"pith:IB6IDYKJ","schema_version":"1.0","canonical_sha256":"407c81e14902c9e77d3ecd59f73b0d845a012aa70a2cff03e7d1d4f9b42703a8","source":{"kind":"arxiv","id":"2101.07172","version":2},"attestation_state":"computed","paper":{"title":"HarDNet-MSEG: A Simple Encoder-Decoder Polyp Segmentation Neural Network that Achieves over 0.9 Mean Dice and 86 FPS","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chien-Hsiang Huang, Hung-Yu Wu, Youn-Long Lin","submitted_at":"2021-01-18T17:20:11Z","abstract_excerpt":"We propose a new convolution neural network called HarDNet-MSEG for polyp segmentation. It achieves SOTA in both accuracy and inference speed on five popular datasets. For Kvasir-SEG, HarDNet-MSEG delivers 0.904 mean Dice running at 86.7 FPS on a GeForce RTX 2080 Ti GPU. It consists of a backbone and a decoder. The backbone is a low memory traffic CNN called HarDNet68, which has been successfully applied to various CV tasks including image classification, object detection, multi-object tracking and semantic segmentation, etc. The decoder part is inspired by the Cascaded Partial Decoder, known "},"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":"2101.07172","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-01-18T17:20:11Z","cross_cats_sorted":[],"title_canon_sha256":"351fa4256a9b16ea0087a789a747f36d9190a481e5ee01e85fb6504f53963c47","abstract_canon_sha256":"418f748b7a4f573c5cd7159c56cc822ee5c12b80f383ed2dd77ac90e1689b63d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:08:21.943970Z","signature_b64":"0tgzxb+on75gTRdPyfa6u/2PMTsTXgw9BF3LI+0sH2Ti7wROPmbVLYoq8zAImF2UMLXVg1vBGEvY/R2KKZMqCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"407c81e14902c9e77d3ecd59f73b0d845a012aa70a2cff03e7d1d4f9b42703a8","last_reissued_at":"2026-07-05T02:08:21.943586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:08:21.943586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HarDNet-MSEG: A Simple Encoder-Decoder Polyp Segmentation Neural Network that Achieves over 0.9 Mean Dice and 86 FPS","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chien-Hsiang Huang, Hung-Yu Wu, Youn-Long Lin","submitted_at":"2021-01-18T17:20:11Z","abstract_excerpt":"We propose a new convolution neural network called HarDNet-MSEG for polyp segmentation. It achieves SOTA in both accuracy and inference speed on five popular datasets. For Kvasir-SEG, HarDNet-MSEG delivers 0.904 mean Dice running at 86.7 FPS on a GeForce RTX 2080 Ti GPU. It consists of a backbone and a decoder. The backbone is a low memory traffic CNN called HarDNet68, which has been successfully applied to various CV tasks including image classification, object detection, multi-object tracking and semantic segmentation, etc. The decoder part is inspired by the Cascaded Partial Decoder, known "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.07172","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2101.07172/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2101.07172","created_at":"2026-07-05T02:08:21.943643+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.07172v2","created_at":"2026-07-05T02:08:21.943643+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.07172","created_at":"2026-07-05T02:08:21.943643+00:00"},{"alias_kind":"pith_short_12","alias_value":"IB6IDYKJALE6","created_at":"2026-07-05T02:08:21.943643+00:00"},{"alias_kind":"pith_short_16","alias_value":"IB6IDYKJALE6O7J6","created_at":"2026-07-05T02:08:21.943643+00:00"},{"alias_kind":"pith_short_8","alias_value":"IB6IDYKJ","created_at":"2026-07-05T02:08:21.943643+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.07436","citing_title":"RPG-SAM: Reliability-Weighted Prototypes and Geometric Adaptive Threshold Selection for Training-Free One-Shot Polyp Segmentation","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IB6IDYKJALE6O7J6ZVM7OOYNQR","json":"https://pith.science/pith/IB6IDYKJALE6O7J6ZVM7OOYNQR.json","graph_json":"https://pith.science/api/pith-number/IB6IDYKJALE6O7J6ZVM7OOYNQR/graph.json","events_json":"https://pith.science/api/pith-number/IB6IDYKJALE6O7J6ZVM7OOYNQR/events.json","paper":"https://pith.science/paper/IB6IDYKJ"},"agent_actions":{"view_html":"https://pith.science/pith/IB6IDYKJALE6O7J6ZVM7OOYNQR","download_json":"https://pith.science/pith/IB6IDYKJALE6O7J6ZVM7OOYNQR.json","view_paper":"https://pith.science/paper/IB6IDYKJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.07172&json=true","fetch_graph":"https://pith.science/api/pith-number/IB6IDYKJALE6O7J6ZVM7OOYNQR/graph.json","fetch_events":"https://pith.science/api/pith-number/IB6IDYKJALE6O7J6ZVM7OOYNQR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IB6IDYKJALE6O7J6ZVM7OOYNQR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IB6IDYKJALE6O7J6ZVM7OOYNQR/action/storage_attestation","attest_author":"https://pith.science/pith/IB6IDYKJALE6O7J6ZVM7OOYNQR/action/author_attestation","sign_citation":"https://pith.science/pith/IB6IDYKJALE6O7J6ZVM7OOYNQR/action/citation_signature","submit_replication":"https://pith.science/pith/IB6IDYKJALE6O7J6ZVM7OOYNQR/action/replication_record"}},"created_at":"2026-07-05T02:08:21.943643+00:00","updated_at":"2026-07-05T02:08:21.943643+00:00"}