{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:CVLPCOVQYLEB6IMUZQBR6YSWEI","short_pith_number":"pith:CVLPCOVQ","schema_version":"1.0","canonical_sha256":"1556f13ab0c2c81f2194cc031f6256221fb12d5917efe06ae2f74f447a31d3d8","source":{"kind":"arxiv","id":"1607.08022","version":3},"attestation_state":"computed","paper":{"title":"Instance Normalization: The Missing Ingredient for Fast Stylization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Dmitry Ulyanov, Victor Lempitsky","submitted_at":"2016-07-27T10:23:00Z","abstract_excerpt":"It this paper we revisit the fast stylization method introduced in Ulyanov et. al. (2016). We show how a small change in the stylization architecture results in a significant qualitative improvement in the generated images. The change is limited to swapping batch normalization with instance normalization, and to apply the latter both at training and testing times. The resulting method can be used to train high-performance architectures for real-time image generation. The code will is made available on github at https://github.com/DmitryUlyanov/texture_nets. Full paper can be found at arXiv:170"},"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":"1607.08022","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-07-27T10:23:00Z","cross_cats_sorted":[],"title_canon_sha256":"d684058049ed0f928362e4756e7386b4474f4222d9eb3b327e8b9607b608ac20","abstract_canon_sha256":"a79d6d0b5530688115c4b4789258f65c496ecfe5e628b8a23659a84925fd4e0e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:22.536895Z","signature_b64":"sfe9m/ilnENOKZ6sqMM3c7unveIetcgctVg/O5mmhyIZRysKeHEjJV53xGFUmlhCI3djSjRqeQJlLeYZj/3ZCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1556f13ab0c2c81f2194cc031f6256221fb12d5917efe06ae2f74f447a31d3d8","last_reissued_at":"2026-05-18T00:31:22.536224Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:22.536224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Instance Normalization: The Missing Ingredient for Fast Stylization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Dmitry Ulyanov, Victor Lempitsky","submitted_at":"2016-07-27T10:23:00Z","abstract_excerpt":"It this paper we revisit the fast stylization method introduced in Ulyanov et. al. (2016). We show how a small change in the stylization architecture results in a significant qualitative improvement in the generated images. The change is limited to swapping batch normalization with instance normalization, and to apply the latter both at training and testing times. The resulting method can be used to train high-performance architectures for real-time image generation. The code will is made available on github at https://github.com/DmitryUlyanov/texture_nets. Full paper can be found at arXiv:170"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.08022","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":"1607.08022","created_at":"2026-05-18T00:31:22.536336+00:00"},{"alias_kind":"arxiv_version","alias_value":"1607.08022v3","created_at":"2026-05-18T00:31:22.536336+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.08022","created_at":"2026-05-18T00:31:22.536336+00:00"},{"alias_kind":"pith_short_12","alias_value":"CVLPCOVQYLEB","created_at":"2026-05-18T12:30:09.641336+00:00"},{"alias_kind":"pith_short_16","alias_value":"CVLPCOVQYLEB6IMU","created_at":"2026-05-18T12:30:09.641336+00:00"},{"alias_kind":"pith_short_8","alias_value":"CVLPCOVQ","created_at":"2026-05-18T12:30:09.641336+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":38,"internal_anchor_count":22,"sample":[{"citing_arxiv_id":"1906.11478","citing_title":"A Convolutional Decoder for Point Clouds using Adaptive Instance Normalization","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"1907.01144","citing_title":"Disentangled Makeup Transfer with Generative Adversarial Network","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"1907.02959","citing_title":"High-throughput Onboard Hyperspectral Image Compression with Ground-based CNN Reconstruction","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"1907.03118","citing_title":"Fast Universal Style Transfer for Artistic and Photorealistic Rendering","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"1907.04003","citing_title":"Mean Spectral Normalization of Deep Neural Networks for Embedded Automation","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"1907.07319","citing_title":"Half a Percent of Labels is Enough: Efficient Animal Detection in UAV Imagery using Deep CNNs and Active Learning","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"1907.08845","citing_title":"Order Matters: Shuffling Sequence Generation for Video Prediction","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"1907.10473","citing_title":"Switchable Normalization for Learning-to-Normalize Deep Representation","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"1907.11483","citing_title":"Annotation-Free Cardiac Vessel Segmentation via Knowledge Transfer from Retinal Images","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2002.09053","citing_title":"Adapted Center and Scale Prediction: More Stable and More Accurate","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2406.12632","citing_title":"Cyclic 2.5D Perceptual Loss for Cross-Modal 3D Medical Image Synthesis: T1w MRI to Tau PET","ref_index":75,"is_internal_anchor":true},{"citing_arxiv_id":"2407.13278","citing_title":"Deep Time Series Models: A Comprehensive Survey and Benchmark","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22572","citing_title":"SegGuidedNet: Sub-Region-Aware Attention Supervision for Interpretable Brain Tumor Segmentation","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18591","citing_title":"Randomized Advantage Transformation (RAT): Computing Natural Policy Gradients via Direct Backpropagation","ref_index":71,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19073","citing_title":"Riemannian Networks over Full-Rank Correlation Matrices","ref_index":97,"is_internal_anchor":true},{"citing_arxiv_id":"2509.05288","citing_title":"Learning to accelerate distributed ADMM using graph neural networks","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"1907.05600","citing_title":"Generative Modeling by Estimating Gradients of the Data Distribution","ref_index":57,"is_internal_anchor":true},{"citing_arxiv_id":"2511.18539","citing_title":"TimePre: Bridging Accuracy, Efficiency, and Stability in Probabilistic Time-Series Forecasting","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2401.04722","citing_title":"U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2603.08032","citing_title":"GCGNet: Graph-Consistent Generative Network for Time Series Forecasting with Exogenous Variables","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08193","citing_title":"Normalization Equivariance for Arbitrary Backbones, with Application to Image Denoising","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14521","citing_title":"Enjoy Your Layer Normalization with the Computational Efficiency of RMSNorm","ref_index":104,"is_internal_anchor":true},{"citing_arxiv_id":"2211.14730","citing_title":"A Time Series is Worth 64 Words: Long-term Forecasting with Transformers","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11131","citing_title":"USEMA: a Scalable Efficient Mamba Like Attention for Medical Image Segmentation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2104.13478","citing_title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","ref_index":94,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CVLPCOVQYLEB6IMUZQBR6YSWEI","json":"https://pith.science/pith/CVLPCOVQYLEB6IMUZQBR6YSWEI.json","graph_json":"https://pith.science/api/pith-number/CVLPCOVQYLEB6IMUZQBR6YSWEI/graph.json","events_json":"https://pith.science/api/pith-number/CVLPCOVQYLEB6IMUZQBR6YSWEI/events.json","paper":"https://pith.science/paper/CVLPCOVQ"},"agent_actions":{"view_html":"https://pith.science/pith/CVLPCOVQYLEB6IMUZQBR6YSWEI","download_json":"https://pith.science/pith/CVLPCOVQYLEB6IMUZQBR6YSWEI.json","view_paper":"https://pith.science/paper/CVLPCOVQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1607.08022&json=true","fetch_graph":"https://pith.science/api/pith-number/CVLPCOVQYLEB6IMUZQBR6YSWEI/graph.json","fetch_events":"https://pith.science/api/pith-number/CVLPCOVQYLEB6IMUZQBR6YSWEI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CVLPCOVQYLEB6IMUZQBR6YSWEI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CVLPCOVQYLEB6IMUZQBR6YSWEI/action/storage_attestation","attest_author":"https://pith.science/pith/CVLPCOVQYLEB6IMUZQBR6YSWEI/action/author_attestation","sign_citation":"https://pith.science/pith/CVLPCOVQYLEB6IMUZQBR6YSWEI/action/citation_signature","submit_replication":"https://pith.science/pith/CVLPCOVQYLEB6IMUZQBR6YSWEI/action/replication_record"}},"created_at":"2026-05-18T00:31:22.536336+00:00","updated_at":"2026-05-18T00:31:22.536336+00:00"}