PiT: Progressive Diffusion Transformer

[2505.13219] PiT: Progressive Diffusion Transformer Skip to main content Search Submit Donate Log in Computer Science > Computer Vision and Pattern Recognition arXiv:2505.13219 (cs) [Submitted on 19 May 2025 ( v1 ), last revised 27 Aug 2026 (this version, v6)] Title: PiT: Progressive Diffusion Transformer Authors: Jiafu Wu , Yabiao Wang , Jian Li , Jinlong Peng , Yun Cao , Chengjie Wang , Jiangning Zhang View PDF HTML (experimental) Abstract: Diffusion Transformers (DiTs) achieve remarkable performance within image generation via the transformer architecture. Conventionally, DiTs are constructed by stacking serial isotropic global modeling transformers, which face significant quadratic computational cost. However, through empirical analysis, we find that DiTs do not rely as heavily on global information as previously believed. In fact, most layers exhibit significant redundancy in global computation. Additionally, conventional attention mechanisms suffer from low-frequency inertia, limiting their efficiency. To address these issues, we propose Pseudo Shifted Window Attention (PSWA), which fundamentally mitigates global attention redundancy. PSWA achieves moderate global-local information through window attention. It further utilizes a high-frequency bridging branch to simulate shifted window operations, which both enrich the high-frequency information and strengthen inter-window connections. Furthermore, we propose the Progressive Coverage Channel Allocation (PCCA) strategy that captures high-order attention without additional computational cost. Based on these innovations, we propose a series of Pseudo Progressive Diffusion Transformer (PiT). Our extensive experiments show their superior performance; for example, our proposed PiT-L achieves 54% FID improvement over DiT-XL/2 while using less computation. Comments: Accepted by Pattern Recognition (PR). DOl: https://doi.org/10.1016/j.patcog.2026.114732 Subjects: Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2505.13219 [cs.CV] (or arXiv:2505.13219v6 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2505.13219 Focus to learn more arXiv-issued DOI via DataCite Journal reference: Pattern Recognition 2026 Related DOI : https://doi.org/10.1016/j.patcog.2026.114732 Focus to learn more DOI(s) linking to related resources Submission history From: Jiafu Wu [ view email ] [v1] Mon, 19 May 2025 15:02:33 UTC (3,504 KB) [v2] Tue, 20 May 2025 03:01:57 UTC (3,504 KB) [v3] Wed, 6 Aug 2025 11:28:19 UTC (912 KB) [v4] Wed, 13 Aug 2025 14:04:04 UTC (2,309 KB) [v5] Thu, 14 Aug 2025 03:15:18 UTC (2,309 KB) [v6] Thu, 27 Aug 2026 09:19:11 UTC (1,821 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.CV < prev | next > new | recent | 2025-05 Change to browse by: cs References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• PiT: Progressive Diffusion Transformer#677377
• CMuon: Accelerating and Stabilizing Diffusion Transformer Training via Chunked Momentum Orthogonalization#424005
• Estimation of the pseudoscalar glueball mass based on a modified Transformer#635551
• Estimation of the pseudoscalar glueball mass based on a modified Transformer#633202
• Learning Nonlinear Responses in PET Bottle Buckling with a Hybrid DeepONet-Transolver Framework#926965