scholarly journals Weakly Supervised Anomaly Segmentation in Retinal OCT Images Using An Adversarial Learning Approach

2021 ◽  
Author(s):  
Guohua Shi ◽  
Jing Wang ◽  
Wanyue Li ◽  
Yiwei Chen ◽  
wangyi Fang ◽  
...  
Keyword(s):  
Learning Approach ◽  
Adversarial Learning ◽  
Weakly Supervised

scholarly journals Weakly supervised anomaly segmentation in retinal OCT images using an adversarial learning approach: publisher’s note

2021 ◽  
Author(s):  
Sarah J. Walker ◽  
Jing Wang ◽  
Wanyue Li ◽  
Yiwei Chen ◽  
wangyi Fang ◽  
...  
Keyword(s):  
Learning Approach ◽  
Adversarial Learning ◽  
Weakly Supervised

scholarly journals A weakly supervised deep learning approach for label-free imaging flow-cytometry-based blood diagnostics

2021 ◽  
Vol 1 (6) ◽  
pp. 100094
Author(s):  
Corin F. Otesteanu ◽  
Martina Ugrinic ◽  
Gregor Holzner ◽  
Yun-Tsan Chang ◽  
Christina Fassnacht ◽  
...  
Keyword(s):  
Flow Cytometry ◽  
Deep Learning ◽  
Learning Approach ◽  
Label Free ◽  
Imaging Flow Cytometry ◽  
Weakly Supervised

scholarly journals Generative Adversarial Neural Architecture Search

2021 ◽  
Author(s):  
Seyed Saeed Changiz Rezaei ◽  
Fred X. Han ◽  
Di Niu ◽  
Mohammad Salameh ◽  
Keith Mills ◽  
...  
Keyword(s):  
Deep Learning ◽  
Reinforcement Learning ◽  
Importance Sampling ◽  
Ad Hoc ◽  
Search Space ◽  
Learning Approach ◽  
Adversarial Learning ◽  
Search Spaces ◽  
Neural Architecture ◽  
Empirical Success

Despite the empirical success of neural architecture search (NAS) in deep learning applications, the optimality, reproducibility and cost of NAS schemes remain hard to assess. In this paper, we propose Generative Adversarial NAS (GA-NAS) with theoretically provable convergence guarantees, promoting stability and reproducibility in neural architecture search. Inspired by importance sampling, GA-NAS iteratively fits a generator to previously discovered top architectures, thus increasingly focusing on important parts of a large search space. Furthermore, we propose an efficient adversarial learning approach, where the generator is trained by reinforcement learning based on rewards provided by a discriminator, thus being able to explore the search space without evaluating a large number of architectures. Extensive experiments show that GA-NAS beats the best published results under several cases on three public NAS benchmarks. In the meantime, GA-NAS can handle ad-hoc search constraints and search spaces. We show that GA-NAS can be used to improve already optimized baselines found by other NAS methods, including EfficientNet and ProxylessNAS, in terms of ImageNet accuracy or the number of parameters, in their original search space.

Multi‐frame based adversarial learning approach for video surveillance

2022 ◽  
Vol 122 ◽  
pp. 108350
Author(s):  
Prashant W. Patil ◽  
Akshay Dudhane ◽  
Sachin Chaudhary ◽  
Subrahmanyam Murala
Keyword(s):  
Video Surveillance ◽  
Learning Approach ◽  
Adversarial Learning
Sign in / Sign up

Export Citation Format

Share Document