Diffusion models learn to restore noisy data, which is corrupted with different levels of noise, by optimizing the weighted sum of the corresponding loss terms, i.e., denoising score matching loss. In this paper, we show that restoring data corrupted with certain noise levels offers a proper pretext task for the model to learn rich visual concepts. We propose to prioritize such noise levels over other levels during training, by redesigning the weighting scheme of the objective function. We show that our simple redesign of the weighting scheme significantly improves the performance of diffusion models regardless of the datasets, architectures, and sampling strategies.
Efficient Training for Human Video Generation with Entropy-Guided Prioritized Progressive Learning
Stanford University(斯坦福大学);North China Electric Power University(华北电力大学);University of Adelaide(阿德莱德大学);University of Technology Sydney(悉尼技术大学);University of Science and Technology of China(中国科学技术大学)
Implicit and Explicit Language Guidance for Diffusion-based Visual Perception
School of Electrical and Information Engineering, Tianjin University(天津大学电气与信息工程学院);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);School of Big Data and Software Engineering, Chongqing University(重庆大学大数据与软件学院)
Training-Free Rate-Distortion-Perception Traversal With Diffusion
Department of Information Engineering, The Chinese University of Hong Kong, Hong Kong(信息工程系,香港中文大学,香港);College of Electronic and Information Engineering, Shenzhen University, Shenzhen(电子与信息工程学院,深圳大学,深圳)
Knowledge-Aligned Counterfactual-Enhancement Diffusion Perception for Unsupervised Cross-Domain Visual Emotion Recognition
The Laboratory of Intelligent Collaborative Computing of UESTC(UESTC智能协同计算实验室);Ubiquitous Intelligence and Trusted Services Key Laboratory of Sichuan Province(四川省 ubiquitous intelligence and trusted services 重点实验室);Faculty of Information Technology, Monash University(墨尔本大学信息技术学院)
Aligning Diffusion Models with Noise-Conditioned Perception
Artificial Intelligence Research Institute (AIRI)(人工智能研究 institute(AIRI));Skolkovo Institute of Science and Technology(斯克尔科沃科学与技术研究所);HSE University(俄罗斯高等经济学院);Research Center for Trusted Artificial Intelligence, ISP RAS(可信人工智能研究中心,信息与通信技术研究院);ISP RAS(信息与通信技术研究院)
UniGP: Taming Diffusion Transformer for Prior-Preserved Unified Generation and Perception
The Hong Kong University of Science and Technology(香港科学与技术大学);DAMO Academy, Alibaba Group(阿里云达摩院);Hupan Lab(虎扑实验室);Zhejiang University(浙江大学);Tsinghua University(清华大学);The Chinese University of Hong Kong(香港中文大学);Zeekr Automobile R&D Co., Ltd.(小鹏汽车研发有限公司)
Towards Dense and Accurate Radar Perception Via Efficient Cross-Modal Diffusion Model
Huzhou Institute, Zhejiang University(浙江大学湖州研究院);Nanyang Technological University(南洋理工大学);School of Cyber Science and Technology, University of Science and Technology of China(中国科学技术大学网络空间安全学院);Institute of Cyber-Systems and Control, College of Control Science and Engineering, Zhejiang University(浙江大学控制科学与工程学院 cyber系统与控制研究所)
DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception
Shenzhen Key Laboratory for High Performance Data Mining, SIAT, CAS(中国科学院深圳先进技术研究院);University of Chinese Academy of Sciences(中国科学院大学);Tsinghua University(清华大学);Huazhong University of Science and Technology(华中科技大学);University of New South Wales(新南威尔士大学);National University of Singapore(新加坡国立大学);University of Science and Technology of China(中国科学技术大学);The University of Sydney(悉尼大学);Alibaba Group(阿里巴巴集团)
One at a Time: Progressive Multi-step Volumetric Probability Learning for Reliable 3D Scene Perception
Shanghai Jiao Tong University(上海交通大学);Ningbo Institute of Digital Twin, Eastern Institute of Technology(宁波数字孪生研究院,东方理工);Tokyo Institute of Technology(东京工业大学);PhiGent Robotics(PhiGent机器人公司)
Reversible Unfolding Network for Concealed Visual Perception with Generative Refinement
Department of Biomedical Engineering, Duke University(生物医学工程系,杜克大学);Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院);Nankai International Advanced Research Institute (SHENZHEN FUTIAN), Nankai University(南开国际先进研究院(深圳福田),南开大学);College of Computer Science, Nankai University(计算机科学学院,南开大学)
Rendering-Refined Stable Diffusion for Privacy Compliant Synthetic Data
University of California, Davis(加利福尼亚大学戴维斯分校);Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院);Australian National University(澳大利亚国立大学);Sony AI, Sony Research(索尼人工智能,索尼研究院)
Diffusion-Guided Semantic Consistency for Multimodal Heterogeneity
The University of British Columbia(不列颠哥伦比亚大学);Fudan University(复旦大学);Duke Kunshan University(杜克昆山大学);East China Normal University(华东师范大学);University of California, Davis(加州大学戴维斯分校);China University of Mining and Technology(中国矿业大学);SMBU;Shenzhen University(深圳大学)
One Image is All You Need: Agentic One-Shot Image Generation via Text-Based World Models for Long-Tail Spatial Perception
Tsinghua University(清华大学);SenseTime Research(商汤科技研究院);Sun Yat-Sen University(中山大学);Technical University of Munich(慕尼黑工业大学);Heilbronn Data Science Center(海尔布隆数据科学中心);Munich Data Institute(慕尼黑数据研究所)
Representation Learning in Diffusion and Flow-based Model: An Application Aspect
Fudan University(复旦大学);School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University(西北工业大学光学与电子信息人工智能学院(iOPEN));The University of Hong Kong(香港大学)
Active Sampling for Ultra-Low-Bit-Rate Video Compression via Conditional Controlled Diffusion
Department of Electrical and Computer Engineering, University of California San Diego(电子与计算机工程系,加州大学圣地亚哥分校);Department of Electrical and Systems Engineering, University of Pennsylvania(电子与系统工程系,宾夕法尼亚大学)
DiT-JSCC: Rethinking Deep JSCC with Diffusion Transformers and Semantic Representations
Beijing University of Posts and Telecommunications(北京邮电大学);Shanghai Jiao Tong University(上海交通大学);University of Shanghai for Science and Technology(上海科技大学)
Adding Thermal Awareness to Visual Systems in Real-Time via Distilled Diffusion Models
Northwestern University(西北大学);Northeastern University(东北大学);Hong Kong Baptist University(香港 Baptist大学);Beijing Normal - Hong Kong Baptist University(北京师范大学-香港 Baptist大学)