Semantic image segmentation aims to obtain object labels with precise boundaries, which usually suffers from overfitting. Recently, various data augmentation strategies like regional dropout and mix strategies have been proposed to address the problem. These strategies have proved to be effective for guiding the model to attend on less discriminative parts. However, current strategies operate at the image level, and objects and the background are coupled. Thus, the boundaries are not well augmented due to the fixed semantic scenario. In this paper, we propose ObjectAug to perform object-level augmentation for semantic image segmentation. ObjectAug first decouples the image into individual objects and the background using the semantic labels. Next, each object is augmented individually with commonly used augmentation methods (e.g., scaling, shifting, and rotation). Then, the black area brought by object augmentation is further restored using image inpainting. Finally, the augmented objects and background are assembled as an augmented image. In this way, the boundaries can be fully explored in the various semantic scenarios. In addition, ObjectAug can support category-aware augmentation that gives various possibilities to objects in each category, and can be easily combined with existing image-level augmentation methods to further boost performance. Comprehensive experiments are conducted on both natural image and medical image datasets. Experiment results demonstrate that our ObjectAug can evidently improve segmentation performance.
Cutting-Splicing data augmentation: A novel technology for medical image segmentation
Guangdong Provincial People’s Hospital（广东省人民医院）；Guangdong Academy of Medical Sciences（广东省医学科学院）；Guangdong Cardiovascular Institute（广东省心血管病研究所）；Wuhan University（武汉大学）；Guangzhou Women and Children’s Medical Center（广州市妇女儿童医疗中心）；Guangzhou Medical University（广州医科大学）
Adaptive Spatial Augmentation for Semi-supervised Semantic Segmentation
Shaanxi Provincial Key Laboratory of Speech and Image Information Processing（陕西语音图像信息处理省级重点实验室）；National Engineering Laboratory for Integrated Aerospace-Ground-Ocean Big Data Application Technology（集成空天海大数据应用技术国家工程实验室）；School of Computer Science, Northwestern Polytechnical University（西北工业大学计算机学院）；College of Information Engineering, Northwest A&F University（西北农林科技大学信息工程学院）
Task-Specific Data Augmentation and Inference Processing for VIPriors Instance Segmentation Challenge
Ant Group（蚂蚁集团）
实例分割在图像编辑、图像分析、自动驾驶等领域有着广泛的应用，但在实际应用中数据不足是一个普遍的问题。视觉归纳先验（VIPriors）实例分割挑战集中在这个问题上。VIPriors for Data-Efficient计算机视觉Challenges要求参赛者在缺乏数据的环境中从头开始训练模型，但也有一些视觉归纳先验可以使用。为了解决VIPriors的实例分割问题，我们设计了一个特定任务的数据增强（TS-DA）策略和推理处理（TS-IP）策略。特定任务数据增强策略的主要目的是解决数据不足问题。为了充分利用视觉归纳先验知识，我们设计了一种任务特定的推理处理策略。我们证明了所提出的方法的适用性VIPriors实例分割的挑战。所应用的分割模型是基于CBNetV 2主干的Swin-Base上的基于混合任务级联的检测器。实验结果表明，在2022个VIPriors实例分割挑战赛的测试集上，该方法取得了较好的效果，AP@0.50：0.95为0.531.
Adaptive Augmentation-Aware Latent Learning for Robust LiDAR Semantic Segmentation
University of Science and Technology of China（中国科学技术大学）；National Key Laboratory of Deep Space Exploration, Deep Space Exploration Laboratory（深空探测全国重点实验室（深空探测实验室））
Exploring Token-Level Augmentation in Vision Transformer for Semi-Supervised Semantic Segmentation
South China University of Technology（华南理工大学）；Pengcheng Laboratory（鹏城实验室）；China Tobacco Guangdong Industrial Corporation（广东中烟工业有限责任公司）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
CP2M: Clustered-Patch-Mixed Mosaic Augmentation for Aerial Image Segmentation
Northwestern University（西北大学）；Carnegie Mellon University（卡内基梅隆大学）；The University of Hong Kong（香港大学）；Duke University（杜克大学）；University College Dublin（都柏林大学学院）；Beijing University of Technology（北京工业大学）；The ADAPT SFI Research Centre（ADAPT SFI研究中心）
Automatic Data Augmentation via Deep Reinforcement Learning for Effective Kidney Tumor Segmentation
Nanjing University（南京大学）；Medical School of Nanjing University（南京大学医学院）；National Institute of Healthcare Data Science, Nanjing University（南京大学国家健康数据科学研究院）；UNC Chapel Hill（北卡罗来纳大学教堂山分校）
CamoFA: A Learnable Fourier-based Augmentation for Camouflage Segmentation
University of Science, Ho Chi Minh City（胡志明市科学大学）；Vietnam National University, Ho Chi Minh City（胡志明市越南国家大学）；Stony Brook University（石溪大学）；John von Neumann Institute（约翰·冯·诺依曼研究所）；University of Dayton（代顿大学）；Monash University（莫纳什大学）
Test-time generative augmentation for medical image segmentation
organization= School of Computer Science；Engineering, Nanjing University of Science；organization= Bioengineering Department；Imperial-X, Imperial College London , city= London , postcode= W12 7SL , country= UK；organization= Digital Medical Research Center, School of Basic Medical Sciences, Fudan University , city= Shanghai , country= China；organization= Shanghai Key Laboratory of MICCAI , city= Shanghai , country= China；organization= School of Biomedical Engineering, Shenzhen University , city= Shenzhen , country= China；organization= Department of Computer Science；Engineering, The Hong Kong University of Science；Engineering, The Chinese University of Hong Kong , city= Hong Kong , country= China；Lung Institute, Imperial College London , city= London , postcode= SW7 2AZ , country= UK；organization= Cardiovascular Research Centre, Royal Brompton Hospital , city= London , postcode= SW3 6NP , country= UK；organization= School of Biomedical Engineering \& Imaging Sciences, King's College London , city= London , postcode= WC2R 2LS , country= UK
Instance Segmentation Challenge Track Technical Report, VIPriors Workshop at ICCV 2021: Task-Specific Copy-Paste Data Augmentation Method for Instance Segmentation
DIVUS corp.（DIVUS公司）；DeltaX corp.（DeltaX公司）；DP World（DP世界公司）；Kumoh National Institute of Technology（庆熙大学（注：此处原机构名称为Kumoh National Institute of Technology，常见中文名应为“公州大学”，但根据要求保留原文并翻译，此处可能存在翻译准确性问题，需注意））
SRMF: A Data Augmentation and Multimodal Fusion Approach for Long-Tail UHR Satellite Image Segmentation
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；Haina Institute of Zhejiang University, Advanced Technology Institute, Zhejiang University（浙江大学海纳研究院、先进技术研究院）；Binjiang Research Institute of Zhejiang University（浙江大学滨江研究院）
Image Augmentation with Controlled Diffusion for Weakly-Supervised Semantic Segmentation
XJTLU AI University Research Centre（西交利物浦大学AI大学研究中心）；Jiangsu Province Engineering Research Centre of Data Science and Cognitive Computation at XJTLU（西交利物浦大学江苏省数据科学与认知计算工程研究中心）；SIP AI innovation platform（苏州工业园区人工智能创新平台）
A Text-Image Fusion Method with Data Augmentation Capabilities for Referring Medical Image Segmentation
College of Information Science and Engineering（信息科学与工程学院）；Ritsumeikan University（立命馆大学）；Tiwaki Co., Ltd.（Tiwaki公司）；Dalian University of Technology（大连理工大学）；School of Software（软件学院）；Zhejiang University（浙江大学）
Adversarial Attack Driven Data Augmentation for Accurate And Robust Medical Image Segmentation
Tsinghua University（清华大学）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）；Key Laboratory of Pervasive Computing, Ministry of Education（教育部普适计算重点实验室）；Beijing Tsinghua Changgung Hospital, School of Clinical Medicine, Tsinghua University（清华大学临床医学院北京清华长庚医院）；Peking Union Medical College Hospital（北京协和医院）
