Despite their exceptional performance in vision tasks, deep learning models often struggle when faced with domain shifts during testing. Test-Time Training (TTT) methods have recently gained popularity by their ability to enhance the robustness of models through the addition of an auxiliary objective that is jointly optimized with the main task. Being strictly unsupervised, this auxiliary objective is used at test time to adapt the model without any access to labels. In this work, we propose Noise-Contrastive Test-Time Training (NC-TTT), a novel unsupervised TTT technique based on the discrimination of noisy feature maps. By learning to classify noisy views of projected feature maps, and then adapting the model accordingly on new domains, classification performance can be recovered by an important margin. Experiments on several popular test-time adaptation baselines demonstrate the advantages of our method compared to recent approaches for this task. The code can be found at:https://github.com/GustavoVargasHakim/NCTTT.git
U-TTT: Towards Generalizable PET Image Denoising via Test-Time Training
School of Biological Science and Medical Engineering, Beihang University(北京航空航天大学生物科学与医学工程学院);Department of Biomedical Engineering, Tsinghua University(清华大学生物医学工程系);School of Aerospace Engineering, Tsinghua University(清华大学航天航空学院);ByteDance Inc.(字节跳动有限公司)
Data Augmentation of Contrastive Learning is Estimating Positive-incentive Noise
The University of Hong Kong(香港大学);Institute of Artificial Intelligence (TeleAI), China Telecom(中国电信人工智能研究院);Fudan University(复旦大学);School of Artificial Intelligence, OPtics(人工智能学院);ElectroNics (iOPEN), Northwestern Polytechnical University(西北工业大学电子学院)
Global-Graph Guided and Local-Graph Weighted Contrastive Learning for Unified Clustering on Incomplete and Noise Multi-View Data
Guangxi Normal University(广西师范学院);University of Electronic Science and Technology of China(电子科技大学);Singapore University of Technology and Design(新加坡科技设计大学);Hainan University(海南大学)
PRCL: Probabilistic Representation Contrastive Learning for Semi-Supervised Semantic Segmentation
School of Computer Science and Engineering, Northeastern University(东北大学计算机科学与工程学院);Intelligent Game and Decision Laboratory(智能游戏与决策实验室);Alibaba DAMO Academy, Alibaba Group(阿里巴巴集团达摩院);Zhejiang University(浙江大学)
A Contrastive Pre-trained Foundation Model for Deciphering Imaging Noisomics across Modalities
College of Biomedical Engineering, Yiwu Research Institute, Fudan University, Shanghai, China(复旦大学生物医学工程学院);Department of Psychological and Cognitive Sciences, Tsinghua University, Beijing, China(清华大学心理学与认知科学系);Shanghai Innovation Institute, Shanghai, China(上海创新研究院);DAMO Academy, Alibaba Group, Beijing, China(阿里云达摩院);Hupan Laboratory, Hangzhou, Zhejiang, China(华平实验室)
Prior-guided Hierarchical Instance-pixel Contrastive Learning for Ultrasound Speckle Noise Suppression
School of Biological Science and Medical Engineering, Southeast University(生物科学与医学工程学院,东南大学);Department of Biomedical Engineering, The Ohio State University(生物医学工程系,奥斯特大学);Jiangsu Key Laboratory of Biomaterials and Devices, Southeast University(江苏省生物材料与器件重点实验室,东南大学);State Key Laboratory of Digital Medical Engineering, Southeast University(国家数字医学工程重点实验室,东南大学)
NCL-CIR: Noise-aware Contrastive Learning for Composed Image Retrieval
Hong Kong Baptist University(香港 Baptist 大学);BNU-HKBU United International College(BNU-HKBU 国际学院);University of Wollongong(沃林根大学);University of Surrey(萨里大学)
PointCAT: Contrastive Adversarial Training for Robust Point Cloud Recognition
University of Science and Technology of China(中国科学技术大学);Microsoft Research(微软研究院);Simon Fraser University(西蒙弗雷泽大学);Wormpex AI Research LLC(Wormpex人工智能研究有限责任公司)
Enhanced Low-resolution LiDAR-Camera Calibration Via Depth Interpolation and Supervised Contrastive Learning
Arizona State University(亚利桑那州立大学);U.S. Army DEVCOM Research Laboratory(美国陆军作战能力发展司令部研究实验室);U.S. Army DEVCOM C5ISR Center(美国陆军作战能力发展司令部指挥、控制、通信、计算机、网络、情报、监视与侦察中心)
Coherence-Guided Pyramid Self-Contrastive Disentanglement for Adaptive IQ Signal Denoising in Synthetic Aperture Ultrasound
Department of Electrical and Computer Engineering, The University of Hong Kong(香港大学电子与计算机工程系);Department of Biomedical Engineering, Duke University(达特茅斯大学生物医学工程系)
Jo-SRC: A Contrastive Approach for Combating Noisy Labels
Nanjing University of Science and Technology(南京理工大学);University of Electronic Science and Technology of China(电子科技大学);The University of Adelaide(阿德莱德大学);University of Technology Sydney(悉尼科技大学)
由于深度神经网络(DNN)中的记忆效应,使用噪声标签进行训练通常会导致模型性能较差。现有的最先进的方法主要采用样本选择策略,其选择小损失样本用于后续训练。然而,现有文献倾向于在每个小批次内进行样本选择,忽略了不同小批次中噪声比的不平衡。此外,高损失样本中的宝贵知识被浪费了。为此,我们提出了一种抗噪声的方法Jo-SRC(Joint Sample Selection and Model Regularization based on Consistency)。具体来说,我们以对比学习的方式训练网络。从两个不同的角度对每个样本进行预测,以估计其干净或分布外的“可能性”。此外,我们提出了一个联合损失,以提高模型的推广性能,通过引入一致性正则化。大量的实验已经验证了我们的方法优于现有的国家的最先进的方法。