SeiT: Storage-efficient vision training with tokens using 1% of pixel storageJan 1, 2023·Song Park,Sanghyuk Chun,Byeongho Heo,Wonjae Kim,Sangdoo Yun· 0 min read PDF Cite CodeTypeConference paperPublicationProceedings of the IEEE/CVF International Conference on Computer VisionLast updated on Jan 1, 2023 AuthorsSong ParkResearch Scientist ← Similarity of neural architectures using adversarial attack transferability Jan 1, 2024Eccv caption: Correcting false negatives by collecting machine-and-human-verified image-caption associations for ms-coco Jan 1, 2022 →
