{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FHHTDSMJUZKWV4SRJ4OYCYNKCY","short_pith_number":"pith:FHHTDSMJ","schema_version":"1.0","canonical_sha256":"29cf31c989a6556af2514f1d8161aa160066738e7edd6984af3dee2cc165246a","source":{"kind":"arxiv","id":"2111.13824","version":4},"attestation_state":"computed","paper":{"title":"FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Peiqin Sun, Shuchang Zhou, Tianyu Zhang, Yang Lin, Zheng Li","submitted_at":"2021-11-27T06:20:53Z","abstract_excerpt":"Network quantization significantly reduces model inference complexity and has been widely used in real-world deployments. However, most existing quantization methods have been developed mainly on Convolutional Neural Networks (CNNs), and suffer severe degradation when applied to fully quantized vision transformers. In this work, we demonstrate that many of these difficulties arise because of serious inter-channel variation in LayerNorm inputs, and present, Power-of-Two Factor (PTF), a systematic method to reduce the performance degradation and inference complexity of fully quantized vision tra"},"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":"2111.13824","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-27T06:20:53Z","cross_cats_sorted":[],"title_canon_sha256":"244c2312451ab9058ad8e0fda8b4be08b23ccc453d01b6359c317b09cb592b2d","abstract_canon_sha256":"ca72c4861bd7c3592b2632b89137f0c1057785e8e9cc0cd159b43e532b55748e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:42:46.975137Z","signature_b64":"bpKQ34CwZiFHIk6SydoUVDj7qnJXwqo/8g6tyO8xde6bSMgMRaMUrXe5Il8PWF6ytHMCfOT6zBra+b/JYWMqAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29cf31c989a6556af2514f1d8161aa160066738e7edd6984af3dee2cc165246a","last_reissued_at":"2026-07-05T05:42:46.974604Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:42:46.974604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Peiqin Sun, Shuchang Zhou, Tianyu Zhang, Yang Lin, Zheng Li","submitted_at":"2021-11-27T06:20:53Z","abstract_excerpt":"Network quantization significantly reduces model inference complexity and has been widely used in real-world deployments. However, most existing quantization methods have been developed mainly on Convolutional Neural Networks (CNNs), and suffer severe degradation when applied to fully quantized vision transformers. In this work, we demonstrate that many of these difficulties arise because of serious inter-channel variation in LayerNorm inputs, and present, Power-of-Two Factor (PTF), a systematic method to reduce the performance degradation and inference complexity of fully quantized vision tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.13824","kind":"arxiv","version":4},"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/2111.13824/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":"2111.13824","created_at":"2026-07-05T05:42:46.974670+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.13824v4","created_at":"2026-07-05T05:42:46.974670+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.13824","created_at":"2026-07-05T05:42:46.974670+00:00"},{"alias_kind":"pith_short_12","alias_value":"FHHTDSMJUZKW","created_at":"2026-07-05T05:42:46.974670+00:00"},{"alias_kind":"pith_short_16","alias_value":"FHHTDSMJUZKWV4SR","created_at":"2026-07-05T05:42:46.974670+00:00"},{"alias_kind":"pith_short_8","alias_value":"FHHTDSMJ","created_at":"2026-07-05T05:42:46.974670+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21947","citing_title":"ScalePredictor: Instance-aware Scale Learning for Accurate Quantization of Vision Transformers","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01798","citing_title":"Approximate Attention Weighting for Sustainable FPGA-Based Vision Transformer Inference","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04373","citing_title":"Selective Coupling of Decoupled Informative Regions: Masked Attention Alignment for Data-Free Quantization of Vision Transformers","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2503.03088","citing_title":"AHCQ-SAM: Toward Accurate and Hardware-Compatible Post-Training Segment Anything Model Quantization","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16901","citing_title":"CAR-SAM: Cross-Attention Reconstruction for Post-Training Quantization of the Segment Anything Model","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25306","citing_title":"QFlash: Bridging Quantization and Memory Efficiency in Vision Transformer Attention","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01330","citing_title":"Colinearity Decay: Training Quantization-Friendly ViTs with Outlier Decay","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FHHTDSMJUZKWV4SRJ4OYCYNKCY","json":"https://pith.science/pith/FHHTDSMJUZKWV4SRJ4OYCYNKCY.json","graph_json":"https://pith.science/api/pith-number/FHHTDSMJUZKWV4SRJ4OYCYNKCY/graph.json","events_json":"https://pith.science/api/pith-number/FHHTDSMJUZKWV4SRJ4OYCYNKCY/events.json","paper":"https://pith.science/paper/FHHTDSMJ"},"agent_actions":{"view_html":"https://pith.science/pith/FHHTDSMJUZKWV4SRJ4OYCYNKCY","download_json":"https://pith.science/pith/FHHTDSMJUZKWV4SRJ4OYCYNKCY.json","view_paper":"https://pith.science/paper/FHHTDSMJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.13824&json=true","fetch_graph":"https://pith.science/api/pith-number/FHHTDSMJUZKWV4SRJ4OYCYNKCY/graph.json","fetch_events":"https://pith.science/api/pith-number/FHHTDSMJUZKWV4SRJ4OYCYNKCY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FHHTDSMJUZKWV4SRJ4OYCYNKCY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FHHTDSMJUZKWV4SRJ4OYCYNKCY/action/storage_attestation","attest_author":"https://pith.science/pith/FHHTDSMJUZKWV4SRJ4OYCYNKCY/action/author_attestation","sign_citation":"https://pith.science/pith/FHHTDSMJUZKWV4SRJ4OYCYNKCY/action/citation_signature","submit_replication":"https://pith.science/pith/FHHTDSMJUZKWV4SRJ4OYCYNKCY/action/replication_record"}},"created_at":"2026-07-05T05:42:46.974670+00:00","updated_at":"2026-07-05T05:42:46.974670+00:00"}