{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NCSVYBOES5SG2GVSSXFQLOCY6Q","short_pith_number":"pith:NCSVYBOE","schema_version":"1.0","canonical_sha256":"68a55c05c497646d1ab295cb05b858f408bfb29c561cc520890cfa320676a11e","source":{"kind":"arxiv","id":"2104.04767","version":2},"attestation_state":"computed","paper":{"title":"MobileStyleGAN: A Lightweight Convolutional Neural Network for High-Fidelity Image Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Sergei Belousov","submitted_at":"2021-04-10T13:46:49Z","abstract_excerpt":"In recent years, the use of Generative Adversarial Networks (GANs) has become very popular in generative image modeling. While style-based GAN architectures yield state-of-the-art results in high-fidelity image synthesis, computationally, they are highly complex. In our work, we focus on the performance optimization of style-based generative models. We analyze the most computationally hard parts of StyleGAN2, and propose changes in the generator network to make it possible to deploy style-based generative networks in the edge devices. We introduce MobileStyleGAN architecture, which has x3.5 fe"},"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":"2104.04767","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-10T13:46:49Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"27ba59a084032ead3a89519e8b06e6252980ff7565bdfaacecb83985ddad7aac","abstract_canon_sha256":"30892aca0e73f2c694bb60c50df8997bc4d147f19325bf34b0f867aac4ec045a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:02.757836Z","signature_b64":"RFLWp4x5e6dsYfLI3lpVg9HKyX+gC0LDr/NnWKlSdQbK0dUQHC7H4rZBaoE9z+ewruP4x27YBFoyTqwO3KHNDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68a55c05c497646d1ab295cb05b858f408bfb29c561cc520890cfa320676a11e","last_reissued_at":"2026-07-05T03:13:02.757465Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:02.757465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MobileStyleGAN: A Lightweight Convolutional Neural Network for High-Fidelity Image Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Sergei Belousov","submitted_at":"2021-04-10T13:46:49Z","abstract_excerpt":"In recent years, the use of Generative Adversarial Networks (GANs) has become very popular in generative image modeling. While style-based GAN architectures yield state-of-the-art results in high-fidelity image synthesis, computationally, they are highly complex. In our work, we focus on the performance optimization of style-based generative models. We analyze the most computationally hard parts of StyleGAN2, and propose changes in the generator network to make it possible to deploy style-based generative networks in the edge devices. We introduce MobileStyleGAN architecture, which has x3.5 fe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.04767","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/2104.04767/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":"2104.04767","created_at":"2026-07-05T03:13:02.757522+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.04767v2","created_at":"2026-07-05T03:13:02.757522+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.04767","created_at":"2026-07-05T03:13:02.757522+00:00"},{"alias_kind":"pith_short_12","alias_value":"NCSVYBOES5SG","created_at":"2026-07-05T03:13:02.757522+00:00"},{"alias_kind":"pith_short_16","alias_value":"NCSVYBOES5SG2GVS","created_at":"2026-07-05T03:13:02.757522+00:00"},{"alias_kind":"pith_short_8","alias_value":"NCSVYBOE","created_at":"2026-07-05T03:13:02.757522+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.11193","citing_title":"Light-T2M: A Lightweight and Fast Model for Text-to-motion Generation","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NCSVYBOES5SG2GVSSXFQLOCY6Q","json":"https://pith.science/pith/NCSVYBOES5SG2GVSSXFQLOCY6Q.json","graph_json":"https://pith.science/api/pith-number/NCSVYBOES5SG2GVSSXFQLOCY6Q/graph.json","events_json":"https://pith.science/api/pith-number/NCSVYBOES5SG2GVSSXFQLOCY6Q/events.json","paper":"https://pith.science/paper/NCSVYBOE"},"agent_actions":{"view_html":"https://pith.science/pith/NCSVYBOES5SG2GVSSXFQLOCY6Q","download_json":"https://pith.science/pith/NCSVYBOES5SG2GVSSXFQLOCY6Q.json","view_paper":"https://pith.science/paper/NCSVYBOE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.04767&json=true","fetch_graph":"https://pith.science/api/pith-number/NCSVYBOES5SG2GVSSXFQLOCY6Q/graph.json","fetch_events":"https://pith.science/api/pith-number/NCSVYBOES5SG2GVSSXFQLOCY6Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NCSVYBOES5SG2GVSSXFQLOCY6Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NCSVYBOES5SG2GVSSXFQLOCY6Q/action/storage_attestation","attest_author":"https://pith.science/pith/NCSVYBOES5SG2GVSSXFQLOCY6Q/action/author_attestation","sign_citation":"https://pith.science/pith/NCSVYBOES5SG2GVSSXFQLOCY6Q/action/citation_signature","submit_replication":"https://pith.science/pith/NCSVYBOES5SG2GVSSXFQLOCY6Q/action/replication_record"}},"created_at":"2026-07-05T03:13:02.757522+00:00","updated_at":"2026-07-05T03:13:02.757522+00:00"}