Diffusion models have proven to be highly effective in image and video generation; however, they encounter challenges in the correct composition of objects when generating images of varying sizes due to single-scale training data. Adapting large pre-trained diffusion models to higher resolution demands substantial computational and optimization resources, yet achieving generation capabilities comparable to low-resolution models remains challenging. This paper proposes a novel self-cascade diffusion model that leverages the knowledge gained from a well-trained low-resolution image/video generation model, enabling rapid adaptation to higher-resolution generation. Building on this, we employ the pivot replacement strategy to facilitate a tuning-free version by progressively leveraging reliable semantic guidance derived from the low-resolution model. We further propose to integrate a sequence of learnable multi-scale upsampler modules for a tuning version capable of efficiently learning structural details at a new scale from a small amount of newly acquired high-resolution training data. Compared to full fine-tuning, our approach achieves a $5\times$ training speed-up and requires only 0.002M tuning parameters. Extensive experiments demonstrate that our approach can quickly adapt to higher-resolution image and video synthesis by fine-tuning for just $10k$ steps, with virtually no additional inference time.
ZeroSmooth: Training-free Diffuser Adaptation for High Frame Rate Video Generation
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Tencent AI Lab（腾讯AI实验室）
LILAC: Layer-Wise Independent LoRAs and Cascaded Conditioning for Multi-Concept Customization of Diffusion Models
Adobe Research, Romania（罗马尼亚Adobe研究院）；Department of Computer Science, University of Bucharest, Romania（罗马尼亚布加勒斯特大学计算机科学系）；International Computer High School of Bucharest, Romania（罗马尼亚布加勒斯特国际计算机高中）
Adapting Vision Foundation Models with Cascaded Semantics
University of Alabama at Birmingham（阿拉巴马大学伯明翰分校）；Carnegie Mellon University（卡内基梅隆大学）；University of Missouri–Kansas City（密苏里大学堪萨斯城分校）；Northeastern University（东北大学）；Tulane University（杜兰大学）；University of Bristol（布里斯托大学）；Oak Ridge National Laboratory（橡树岭国家实验室）
Test-Time Adaptation with SaLIP: A Cascade of SAM and CLIP for Zero shot Medical Image Segmentation
ML-Labs, Dublin City University（都柏林城市大学 ML-Labs）；ML-Labs, University College Dublin（都柏林大学 ML-Labs）；Centre for Applied AI (CeADAR), University College Dublin（都柏林大学应用人工智能中心 (CeADAR)）；Insight SFI Centre for Data Analytics, Dublin City University（都柏林城市大学 Insight SFI 数据分析中心）
UBTECH Sydney Artificial Intelligence Centre（优必选悉尼人工智能中心）；University of Sydney（悉尼大学）；University of Technology Sydney（悉尼科技大学）；Hangzhou Dianzi University（杭州电子科技大学）
MRIo3DS-Net: A Mutually Reinforcing Images to 3D Surface RNN-like framework for model-adaptation indoor 3D reconstruction
Central China Normal University（华中师范大学）；Hainan Surveying and Mapping Product Quality Supervision and Inspection Station, MNR（自然资源部海南测绘产品质量监督检验站）；Wuhan University（武汉大学）
DART: Domain-Adversarial Residual-Transfer Networks for Unsupervised Cross-Domain Image Classification
Univ. of Electronic Sci & Tech.of China（电子科技大学）；The Chinese University of Hong Kong（香港中文大学）；University of Electronic Science and Technology of China（电子科技大学）；Google Inc.（谷歌公司）；Singapore Management University（新加坡管理大学）
Advancing UWF-SLO Vessel Segmentation with Source-Free Active Domain Adaptation and a Novel Multi-Center Dataset
Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；University of Electronic Science and Technology of China（电子科技大学）；West China Hospital, Sichuan University（四川大学华西医院）；Chengdu First People’s Hospital（成都市第一人民医院）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；The Hong Kong University of Science and Technology（香港科技大学）
