Akshayvarun Subramanya

I am a fourth year PhD student at the Dept. of CSEE of University of Maryland, Baltimore County (UMBC), where I work on Machine learning and Computer vision. My advisor is Prof.Hamed Pirsiavash.

I spent the summer of 2020 as part of Amazon Rekognition working on Object Detection algorithms. I also spent the summer of 2019 at Dolby Laboratories working on generative modeling with Cong Zhou and Vivek Kumar.

I previously worked at Indian Institute of Science, where I was a research assistant for Prof.Venkatesh Babu at the Video Analytics Lab.

I am fortunate to have collaborated with Prof.Jelena Kovacevic and Siheng Chen during my internship at Carnegie Mellon University (CMU) in the summer of 2015.

I completed my undergraduate studies from PES Institute of Technology (now PES University).

Email / Twitter / Google Scholar / CV / LinkedIn

Research

I'm interested in computer vision, machine learning, optimization, graphical models.

	Role of Spatial Context in Adversarial Robustness for Object Detection Aniruddha Saha^, Akshayvarun Subramanya^, Koninika Patil, Hamed Pirsiavash ^equal contribution CVPR2020 Adversarial Machine learning Workshop*, 2020 paper / code / Most fast object detection algorithms rely on using spatial context which we show can lead to decreased adversarial robustness. We propose regularization techniques to improve robustness and also discuss using interpretation algorithms in object detection networks.
	Hidden Trigger Backdoor Attacks Aniruddha Saha, Akshayvarun Subramanya, Hamed Pirsiavash Oral presentation at 34th American Conference on Artificial Intelligence(AAAI), 2020 arxiv / We explore poisoning methods to introduce backdoors in neural networks. The trigger for the backdoor is revealed only during inference and hidden during the model training stage, which gives more capacity to the adversary.
	Fooling Network Interpretation in Image Classification Akshayvarun Subramanya^, Vipin Pillai^, Hamed Pirsiavash ^equal contribution International Conference on Computer vision (ICCV)*, 2019 arxiv / code / We show that popular network interpretation algorithms do not necessarily show the correct reasoning for network’s prediction, by using adversarial examples. Our work highlights the need for developing more robust interpretation tools to analyze a neural network’s prediction.
	BatchOut: Batch-level feature augmentation to improve robustness to adversarial examples Akshayvarun Subramanya, Konda Reddy Mopuri, R Venkatesh Babu 11th Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP), 2018 paper / We propose a novel feature augmentation technique which can lead to improved robustness against multiple adversarial methods.
	Confidence estimation in deep neural networks via density modelling Akshayvarun Subramanya, Suraj Srinivas, R Venkatesh Babu International Conference on Signal Processing and Communications (SPCOM), 2018 arxiv / We show that traditional softmax based confidence measures has drawbacks and propose a new confidence measure based on density modelling approaches. The proposed measure shows improvement for different kinds of noise introduced in images.
	Training Sparse Neural Networks Suraj Srinivas, Akshayvarun Subramanya, R Venkatesh Babu Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Embedded vision workshop, 2017 paper / We propose a new framework of training neural networks which implicitly use sparse computations. We introduce additional gate parameters which help in pruning, resulting in state-of-the-art compression results for neural networks.