Search Results for author: Chankyu Lee

Found 6 papers, 1 papers with code

Fusion-FlowNet: Energy-Efficient Optical Flow Estimation using Sensor Fusion and Deep Fused Spiking-Analog Network Architectures

no code implementations19 Mar 2021 Chankyu Lee, Adarsh Kumar Kosta, Kaushik Roy

Standard frame-based cameras that sample light intensity frames are heavily impacted by motion blur for high-speed motion and fail to perceive scene accurately when the dynamic range is high.

Optical Flow Estimation

Towards Understanding the Effect of Leak in Spiking Neural Networks

no code implementations15 Jun 2020 Sayeed Shafayet Chowdhury, Chankyu Lee, Kaushik Roy

While the leaky models have been argued as more bioplausible, a comparative analysis between models with and without leak from a purely computational point of view demands attention.

Spike-FlowNet: Event-based Optical Flow Estimation with Energy-Efficient Hybrid Neural Networks

1 code implementation ECCV 2020 Chankyu Lee, Adarsh Kumar Kosta, Alex Zihao Zhu, Kenneth Chaney, Kostas Daniilidis, Kaushik Roy

Spiking Neural Networks (SNNs) serve as ideal paradigms to handle event camera outputs, but deep SNNs suffer in terms of performance due to the spike vanishing phenomenon.

Motion Detection Optical Flow Estimation +1

X-CHANGR: Changing Memristive Crossbar Mapping for Mitigating Line-Resistance Induced Accuracy Degradation in Deep Neural Networks

no code implementations29 Jun 2019 Amogh Agrawal, Chankyu Lee, Kaushik Roy

We rank the DNN weights and kernels based on a sensitivity analysis, and re-arrange the columns such that the most sensitive kernels are mapped closer to the drivers, thereby minimizing the impact of errors on the overall accuracy.

Emerging Technologies

A Comprehensive Analysis on Adversarial Robustness of Spiking Neural Networks

no code implementations7 May 2019 Saima Sharmin, Priyadarshini Panda, Syed Shakib Sarwar, Chankyu Lee, Wachirawit Ponghiran, Kaushik Roy

In this work, we present, for the first time, a comprehensive analysis of the behavior of more bio-plausible networks, namely Spiking Neural Network (SNN) under state-of-the-art adversarial tests.

Adversarial Robustness

Cannot find the paper you are looking for? You can Submit a new open access paper.