The task of semantic segmentation requires a model to assign semantic labels to each pixel of an image. However, the performance of such models degrades when deployed in an unseen domain with different data distributions compared to the training domain. We present a new augmentation-driven approach to domain generalization for semantic segmentation using a re-parameterized vision transformer (ReVT) with weight averaging of multiple models after training. We evaluate our approach on several benchmark datasets and achieve state-of-the-art mIoU performance of 47.3% (prior art: 46.3%) for small models and of 50.1% (prior art: 47.8%) for midsized models on commonly used benchmark datasets. At the same time, our method requires fewer parameters and reaches a higher frame rate than the best prior art. It is also easy to implement and, unlike network ensembles, does not add any computational complexity during inference.
Adaptive Feature Fusion Neural Network for Glaucoma Segmentation on Unseen Fundus Images
International Medical College（国际医学院）；Chongqing Medical University（重庆医科大学）；The First Affiliated Hospital of Chongqing Medical University（重庆医科大学第一附属医院）；Centre for Frontier AI Research (CFAR)（前沿人工智能研究中心）；Agency for Science Technology and Research (A*STAR)（新加坡科技研究局）
Auto Seg-Loss: Searching Metric Surrogates for Semantic Segmentation
Tsinghua University（清华大学）；SenseTime Research（商汤科技研究院）；The Chinese University of Hong Kong（香港中文大学）；Qing Yuan Research Institute, Shanghai Jiao Tong University（上海交通大学清源研究院）
RepMLPNet: Hierarchical Vision MLP with Re-parameterized Locality
Beijing National Research Center for Information Science and Technology (BNRist)（北京信息科学与技术国家研究中心）；Tsinghua University（清华大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；MEGVII Technology（旷视科技）；Aberystwyth University（阿伯里斯特威斯大学）
Dual-Adaptive SAM3: Hierarchical Routing over Low-Rank Expert Layers for Parameter-Efficient Medical Image Segmentation
Shenzhen Research Institute, The Chinese University of Hong Kong（香港中文大学深圳研究院）；University of Science and Technology of China（中国科学技术大学）；Nanyang Technological University（南洋理工大学）；Imperial Global Singapore (IGS), Imperial College London（伦敦帝国理工学院新加坡帝国全球（IGS））
HQ-UNet: A Hybrid Quantum-Classical U-Net with a Quantum Bottleneck for Remote Sensing Image Segmentation
Space Applications Centre, Indian Space Research Organisation (ISRO), India（印度空间研究组织（ISRO）空间应用中心）；New-Brunswick Honors College, Rutgers University, New Jersey（新泽西罗格斯大学新不伦瑞克荣誉学院）；Centre of Studies in Resources Engineering, Indian Institute of Technology Bombay（印度理工学院孟买资源工程研究中心）
Active Scene Understanding via Online Semantic Reconstruction
National University of Defense Technology（国防科技大学）；Shenzhen University（深圳大学）；Shenzhen Institutes of Advanced Technology（深圳先进技术研究院）；Technical University of Munich（慕尼黑工业大学）
DPF-Net: Combining Explicit Shape Priors in Deformable Primitive Field for Unsupervised Structural Reconstruction of 3D Objects
National Engineering Laboratory for Brain-inspired Intelligence Technology and Application（脑启发智能技术与应用国家工程实验室）；University of Science and Technology of China（中国科学技术大学）
FVP: Fourier Visual Prompting for Source-Free Unsupervised Domain Adaptation of Medical Image Segmentation
Beihang University（北京航空航天大学）；Zhejiang Lab（之江实验室）；Singapore University of Technology and Design（新加坡科技设计大学）；BioMind Technology Center（BioMind技术中心）；Zhongguancun Laboratory（中关村实验室）
Optical aberrations in autonomous driving: Physics-informed parameterized temperature scaling for neural network uncertainty calibration
Machine Vision Metrology Group of the Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院机器视觉计量组）；Volkswagen Group（大众集团）；Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院）；University of Applied Sciences Duesseldorf (HSD)（杜塞尔多夫应用技术大学）
ConES: Concept Embedding Search for Parameter Efficient Tuning Large Vision Language Models
Sichuan University（四川大学）；West China Hospital, Sichuan University（四川大学华西医院）；Suzhou Institute for Advanced Research, USTC（中国科学技术大学苏州高等研究院）；Shanghai AI Laboratory（上海人工智能实验室）；Sichuan University Pittsburgh Institute（四川大学匹兹堡学院）
