Alert button
Picture for Arnab Mondal

Arnab Mondal

Alert button

Retinal Vessel Segmentation under Extreme Low Annotation: A Generative Adversarial Network Approach

Sep 05, 2018
Avisek Lahiri, Vineet Jain, Arnab Mondal, Prabir Kumar Biswas

Figure 1 for Retinal Vessel Segmentation under Extreme Low Annotation: A Generative Adversarial Network Approach
Figure 2 for Retinal Vessel Segmentation under Extreme Low Annotation: A Generative Adversarial Network Approach
Figure 3 for Retinal Vessel Segmentation under Extreme Low Annotation: A Generative Adversarial Network Approach
Figure 4 for Retinal Vessel Segmentation under Extreme Low Annotation: A Generative Adversarial Network Approach

Contemporary deep learning based medical image segmentation algorithms require hours of annotation labor by domain experts. These data hungry deep models perform sub-optimally in the presence of limited amount of labeled data. In this paper, we present a data efficient learning framework using the recent concept of Generative Adversarial Networks; this allows a deep neural network to perform significantly better than its fully supervised counterpart in low annotation regime. The proposed method is an extension of our previous work with the addition of a new unsupervised adversarial loss and a structured prediction based architecture. To the best of our knowledge, this work is the first demonstration of an adversarial framework based structured prediction model for medical image segmentation. Though generic, we apply our method for segmentation of blood vessels in retinal fundus images. We experiment with extreme low annotation budget (0.8 - 1.6% of contemporary annotation size). On DRIVE and STARE datasets, the proposed method outperforms our previous method and other fully supervised benchmark models by significant margins especially with very low number of annotated examples. In addition, our systematic ablation studies suggest some key recipes for successfully training GAN based semi-supervised algorithms with an encoder-decoder style network architecture.

* * First 3 authors contributed equally 
Viaarxiv icon

Low Cost Autonomous Navigation and Control of a Mechanically Balanced Bicycle with Dual Locomotion Mode

Nov 01, 2016
Ayush Pandey, Subhamoy Mahajan, Adarsh Kosta, Dhananjay Yadav, Vikas Pandey, Saurav Sahay, Siddharth Jha, Shubh Agarwal, Aashay Bhise, Raushan Kumar, Aniket Bhushan, Vraj Parikh, Ankit Lohani, Saurabh Dash, Himanshu Choudhary, Rahul Kumar, Anurag Sharma, Arnab Mondal, Chendika Karthik Sai, P N Vamshi

Figure 1 for Low Cost Autonomous Navigation and Control of a Mechanically Balanced Bicycle with Dual Locomotion Mode
Figure 2 for Low Cost Autonomous Navigation and Control of a Mechanically Balanced Bicycle with Dual Locomotion Mode
Figure 3 for Low Cost Autonomous Navigation and Control of a Mechanically Balanced Bicycle with Dual Locomotion Mode
Figure 4 for Low Cost Autonomous Navigation and Control of a Mechanically Balanced Bicycle with Dual Locomotion Mode

On the lines of the huge and varied efforts in the field of automation with respect to technology development and innovation of vehicles to make them run autonomously, this paper presents an innovation to a bicycle. A normal daily use bicycle was modified at low cost such that it runs autonomously, while maintaining its original form i.e. the manual drive. Hence, a bicycle which could be normally driven by any human and with a press of switch could run autonomously according to the needs of the user has been developed.

* ITEC India, Publication Year : 2015. Pages 1 - 10  
* Published in the International Transportation Electrification Conference (ITEC) in 2015 organized by IEEE Industrial Application Society (IAS) and SAE India in Chennai, India 
Viaarxiv icon