Results 261 to 270 of about 5,739,313 (302)

Reciprocal Adversarial Learning for Brain Tumor Segmentation: A Solution to BraTS Challenge 2021 Segmentation Task

BrainLes@MICCAI, 2022
This paper proposes an adversarial learning based training approach for brain tumor segmentation task. In this concept, the 3D segmentation network learns from dual reciprocal adversarial learning approaches.
Himashi Peiris, Zhaolin Chen, Gary F. Egan, Mehrtash Harandi   +3 more
semanticscholar   +1 more source

Self-Supervised Vessel Segmentation via Adversarial Learning

IEEE International Conference on Computer Vision, 2021
Vessel segmentation is critically essential for diagnosing a series of diseases, e.g., coronary artery disease and retinal disease. However, annotating vessel segmentation maps of medical images is notoriously challenging due to the tiny and complex ...
Yuxin Ma, Yang Hua, Hanming Deng, Tao Song, Hao Wang, Zhengui Xue, Heng Cao, Ruhui Ma, Haibing Guan   +8 more
semanticscholar   +1 more source

Miss Detection vs. False Alarm: Adversarial Learning for Small Object Segmentation in Infrared Images

IEEE International Conference on Computer Vision, 2019
A key challenge of infrared small object segmentation (ISOS) is to balance miss detection (MD) and false alarm (FA). This usually needs ``opposite'' strategies to suppress the two terms, and has not been well resolved in the literature. In this paper, we
Huan Wang, Luping Zhou, Lei Wang
semanticscholar   +1 more source

Collaborative and Adversarial Learning of Focused and Dispersive Representations for Semi-supervised Polyp Segmentation

IEEE International Conference on Computer Vision, 2021
Automatic polyp segmentation from colonoscopy images is an essential step in computer aided diagnosis for colorectal cancer. Most of polyp segmentation methods reported in recent years are based on fully supervised deep learning.
Huisi Wu, Guilian Chen, Zhenkun Wen, Jing Qin   +3 more
semanticscholar   +1 more source

Recurrent Multi-Frame Deraining: Combining Physics Guidance and Adversarial Learning

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
Existing video rain removal methods mainly focus on rain streak removal and are solely trained based on the synthetic data, which neglect more complex degradation factors, e.g., rain accumulation, and the prior knowledge in real rain data.
Wenhan Yang, R. Tan, Jiashi Feng, Shiqi Wang, Bin Cheng, Jiaying Liu   +5 more
semanticscholar   +1 more source

Prior-Guided Adversarial Learning With Hypergraph for Predicting Abnormal Connections in Alzheimer’s Disease

IEEE Transactions on Cybernetics
Alzheimer’s disease (AD) is characterized by alterations of the brain’s structural and functional connectivity during its progressive degenerative processes. Existing auxiliary diagnostic methods have accomplished the classification task, but few of them
Qiankun Zuo, Huisi Wu, C. L. P. Chen, Baiying Lei, Shuqiang Wang   +4 more
semanticscholar   +1 more source

Distributionally Adversarial Learning

2021
Adversarial machines, where a learner competes against an adversary, have regained much recent interest in machine learning. This presentation will start with distributionally robust optimization (DRO), introducing our work on adversarial prediction.
openaire   +1 more source

Generalized Wireless Adversarial Deep Learning

Computer Networks, 2020
Deep learning techniques can classify spectrum phenomena (e.g., waveform modulation) with accuracy levels that were once thought impossible. Although we have recently seen many advances in this field, extensive work in computer vision has demonstrated that an adversary can "crack" a classifier by designing inputs that "steer" the classifier away from ...
Francesco Restuccia, Salvatore D'Oro, Amani Al-Shawabka, Bruno Costa Rendon, Kaushik Chowdhury, Stratis Ioannidis, Tommaso Melodia   +6 more
openaire   +1 more source

Adversarial Active Learning

Proceedings of the 2014 Workshop on Artificial Intelligent and Security Workshop, 2014
Active learning is an area of machine learning examining strategies for allocation of finite resources, particularly human labeling efforts and to an extent feature extraction, in situations where available data exceeds available resources. In this open problem paper, we motivate the necessity of active learning in the security domain, identify ...
Brad Miller, Alex Kantchelian, Sadia Afroz, Rekha Bachwani, Edwin Dauber, Ling Huang, Michael Carl Tschantz, Anthony D. Joseph, J.D. Tygar   +8 more
openaire   +1 more source

LESSON: Multi-Label Adversarial False Data Injection Attack for Deep Learning Locational Detection

IEEE Transactions on Dependable and Secure Computing
Deep learning methods can not only detect false data injection attacks (FDIA) but also locate attacks of FDIA. Although adversarial false data injection attacks (AFDIA) based on deep learning vulnerabilities have been studied in the field of single-label
Jiwei Tian, Chao Shen, Buhong Wang, Xiaofang Xia, Meng Zhang, Chenhao Lin, Qian Li   +6 more
semanticscholar   +1 more source