Kaushik Roy

16

Papers

10

Total Citations

Papers (16)

SAP: Corrective Machine Unlearning with Scaled Activation Projection for Label Noise Robustness

DCT-CryptoNets: Scaling Private Inference in the Frequency Domain

CODE-CL: Conceptor-Based Gradient Projection for Deep Continual Learning

Memorization Through the Lens of Curvature of Loss Function Around Samples

Vec2Face: Unveil Human Faces From Their Blackbox Features in Face Recognition

RMP-SNN: Residual Membrane Potential Neuron for Enabling Deeper High-Accuracy and Low-Latency Spiking Neural Network

DCT-SNN: Using DCT To Distribute Spatial Information Over Time for Low-Latency Spiking Neural Networks

Event-based Temporally Dense Optical Flow Estimation with Sequential Learning

Deep Spiking Neural Network: Energy Efficiency Through Time based Coding

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

Inherent Adversarial Robustness of Deep Spiking Neural Networks: Effects of Discrete Input Encoding and Non-Linear Activations

Towards Ultra Low Latency Spiking Neural Networks for Vision and Sequential Tasks Using Temporal Pruning

Samples With Low Loss Curvature Improve Data Efficiency

PIXELS: Progressive Image Xemplar-based Editing with Latent Surgery

Unveiling Privacy, Memorization, and Input Curvature Links

Global Update Tracking: A Decentralized Learning Algorithm for Heterogeneous Data