{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:58:09Z","timestamp":1777888689718,"version":"3.51.4"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376292,U21A20470"],"award-info":[{"award-number":["62376292,U21A20470"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01616","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"17401-17410","source":"Crossref","is-referenced-by-count":0,"title":["Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention Into Convolutions"],"prefix":"10.1109","author":[{"given":"Ziyi","family":"Dong","sequence":"first","affiliation":[{"name":"Sun Yat-sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengxing","family":"Zhou","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weijian","family":"Deng","sequence":"additional","affiliation":[{"name":"Australian National University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengxu","family":"Wei","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyang","family":"Ji","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Lin","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"536","article-title":"On the Theory of Filter Amplifiers","volume":"7","author":"Butterworth","year":"1930","journal-title":"Experimental Wireless & the Wireless Engineer"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i15.33722"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01092"},{"key":"ref7","article-title":"Scalable high-resolution pixel-space image synthesis with hourglass diffusion transformers","volume-title":"In International Conference on Machine Learning","author":"Crowson","year":"2024"},{"key":"ref8","article-title":"Transformers are ssms: Generalized models and efficient algorithms through structured state space duality","volume-title":"In International Conference on Machine Learning","author":"Dao","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref10","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"CoRR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00684"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00599"},{"key":"ref13","article-title":"Classifier-free diffusion guidance","volume-title":"In NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications","author":"Ho","year":"2021"},{"key":"ref14","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"In Advances in Neural Information Processing Systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2106.12423"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1926"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02282"},{"key":"ref18","volume-title":"Flux","year":"2024"},{"key":"ref19","article-title":"Controllable text-to-image generation","author":"Li","year":"2019","journal-title":"In Advances in Neural Information Processing Systems"},{"key":"ref20","article-title":"Faster diffusion via temporal attention decomposition","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Linfusion: 1 gpu, 1 minute, 16k image","author":"Liu","year":"2024","journal-title":"CoRR"},{"key":"ref22","article-title":"More control for free! image synthesis with semantic diffusion guidance","volume-title":"CoRR","author":"Liu","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref24","article-title":"Token caching for diffusion transformer acceleration","author":"Lou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-025-1562-4"},{"key":"ref26","article-title":"Understanding the effective receptive field in deep convolutional neural networks","author":"Luo","year":"2016","journal-title":"In Advances in Neural Information Processing Systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"ref28","first-page":"16784","article-title":"GLIDE: towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"In International Conference on Machine Learning","author":"Quinn Nichol","year":"2022"},{"key":"ref29","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Res., 2024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref31","article-title":"SDXL: improving latent diffusion models for high-resolution image synthesis","volume-title":"CoRR","author":"Podell","year":"2023"},{"key":"ref32","volume-title":"Digital signal processing (3rd ed.): principles, algorithms, and applications","author":"Proakis","year":"1996"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref35","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"CoRR"},{"key":"ref36","first-page":"30105","article-title":"Stylegan-t: Unlocking the power of gans for fast large-scale text-to-image synthesis","volume-title":"In International Conference on Machine Learning","author":"Sauer","year":"2023"},{"key":"ref37","author":"Schuhmann","year":"2023","journal-title":"Laion-5b: A large-scale dataset for training ai models"},{"key":"ref38","article-title":"Fora: Fast-forward caching in diffusion transformer acceleration","author":"Selvaraju","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Denoising diffusion implicit models","volume-title":"In International Conference on Learning Representations","author":"Song","year":"2021"},{"key":"ref40","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"In International Conference on Learning Representations","author":"Song","year":"2021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0165"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref43","author":"Szyma\u0144ski","year":"2023","journal-title":"text2image-multi-prompt: A multi-prompt dataset for text-to-image generation"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref45","year":"2023","journal-title":"midjourney-v5\u2013202304-clean"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0037"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445264.pdf?arnumber=11445264","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:55:28Z","timestamp":1777611328000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445264\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01616","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}