{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MKXBZ3TMI25HRRP2NGOTQJRU65","short_pith_number":"pith:MKXBZ3TM","schema_version":"1.0","canonical_sha256":"62ae1cee6c46ba78c5fa699d382634f76ef5d371831f4ef93e792df862b52d27","source":{"kind":"arxiv","id":"2411.10346","version":2},"attestation_state":"computed","paper":{"title":"BiDense: Binarization for Dense Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Biao Jia, Cheng Wang, Haotong Qin, Jianjun Zhu, Rui Yin, Wenbo Li, Yong Guo, Yulun Zhang","submitted_at":"2024-11-15T16:46:04Z","abstract_excerpt":"Dense prediction is a critical task in computer vision. However, previous methods often require extensive computational resources, which hinders their real-world application. In this paper, we propose BiDense, a generalized binary neural network (BNN) designed for efficient and accurate dense prediction tasks. BiDense incorporates two key techniques: the Distribution-adaptive Binarizer (DAB) and the Channel-adaptive Full-precision Bypass (CFB). The DAB adaptively calculates thresholds and scaling factors for binarization, effectively retaining more information within BNNs. Meanwhile, the CFB f"},"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":"2411.10346","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-15T16:46:04Z","cross_cats_sorted":[],"title_canon_sha256":"784ac15b921dfcef7e7c6f28f2a006466d8f7157cd6622c470d03d427e47974f","abstract_canon_sha256":"a86b5fadffdcd943135a2258725490c854f6d2a9d2788b66e6292b7a716e7dd7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:32.642538Z","signature_b64":"N3beA60xXeOawv4Kzi8FDl3yzRS59fATL/UzTEVSWnMCFYApowfD5Sc2rtLhEBnO1lsuIKdivtgdxqzzT/dKAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62ae1cee6c46ba78c5fa699d382634f76ef5d371831f4ef93e792df862b52d27","last_reissued_at":"2026-07-05T09:38:32.642057Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:32.642057Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BiDense: Binarization for Dense Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Biao Jia, Cheng Wang, Haotong Qin, Jianjun Zhu, Rui Yin, Wenbo Li, Yong Guo, Yulun Zhang","submitted_at":"2024-11-15T16:46:04Z","abstract_excerpt":"Dense prediction is a critical task in computer vision. However, previous methods often require extensive computational resources, which hinders their real-world application. In this paper, we propose BiDense, a generalized binary neural network (BNN) designed for efficient and accurate dense prediction tasks. BiDense incorporates two key techniques: the Distribution-adaptive Binarizer (DAB) and the Channel-adaptive Full-precision Bypass (CFB). The DAB adaptively calculates thresholds and scaling factors for binarization, effectively retaining more information within BNNs. Meanwhile, the CFB f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10346","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/2411.10346/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":"2411.10346","created_at":"2026-07-05T09:38:32.642112+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.10346v2","created_at":"2026-07-05T09:38:32.642112+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10346","created_at":"2026-07-05T09:38:32.642112+00:00"},{"alias_kind":"pith_short_12","alias_value":"MKXBZ3TMI25H","created_at":"2026-07-05T09:38:32.642112+00:00"},{"alias_kind":"pith_short_16","alias_value":"MKXBZ3TMI25HRRP2","created_at":"2026-07-05T09:38:32.642112+00:00"},{"alias_kind":"pith_short_8","alias_value":"MKXBZ3TM","created_at":"2026-07-05T09:38:32.642112+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.03504","citing_title":"Information-Bottleneck Driven Binary Neural Network for Change Detection","ref_index":76,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MKXBZ3TMI25HRRP2NGOTQJRU65","json":"https://pith.science/pith/MKXBZ3TMI25HRRP2NGOTQJRU65.json","graph_json":"https://pith.science/api/pith-number/MKXBZ3TMI25HRRP2NGOTQJRU65/graph.json","events_json":"https://pith.science/api/pith-number/MKXBZ3TMI25HRRP2NGOTQJRU65/events.json","paper":"https://pith.science/paper/MKXBZ3TM"},"agent_actions":{"view_html":"https://pith.science/pith/MKXBZ3TMI25HRRP2NGOTQJRU65","download_json":"https://pith.science/pith/MKXBZ3TMI25HRRP2NGOTQJRU65.json","view_paper":"https://pith.science/paper/MKXBZ3TM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.10346&json=true","fetch_graph":"https://pith.science/api/pith-number/MKXBZ3TMI25HRRP2NGOTQJRU65/graph.json","fetch_events":"https://pith.science/api/pith-number/MKXBZ3TMI25HRRP2NGOTQJRU65/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MKXBZ3TMI25HRRP2NGOTQJRU65/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MKXBZ3TMI25HRRP2NGOTQJRU65/action/storage_attestation","attest_author":"https://pith.science/pith/MKXBZ3TMI25HRRP2NGOTQJRU65/action/author_attestation","sign_citation":"https://pith.science/pith/MKXBZ3TMI25HRRP2NGOTQJRU65/action/citation_signature","submit_replication":"https://pith.science/pith/MKXBZ3TMI25HRRP2NGOTQJRU65/action/replication_record"}},"created_at":"2026-07-05T09:38:32.642112+00:00","updated_at":"2026-07-05T09:38:32.642112+00:00"}