Kaushik Roy

papers

818

total citations

papers (16)

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

CVPR 2020arXiv

379

citations

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

ECCV 2020arXiv

188

citations

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

ECCV 2020arXiv

108

citations

Global Update Tracking: A Decentralized Learning Algorithm for Heterogeneous Data

NEURIPS 2023arXiv

citations

Unveiling Privacy, Memorization, and Input Curvature Links

ICML 2024arXiv

citations

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

AAAI 2025arXiv

citations

DCT-CryptoNets: Scaling Private Inference in the Frequency Domain

ICLR 2025arXiv

citations

PIXELS: Progressive Image Xemplar-based Editing with Latent Surgery

AAAI 2025arXiv

citations

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

ICCV 2025arXiv

citations

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

ICCV 2021

citations

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

ECCV 2022

citations

Deep Spiking Neural Network: Energy Efficiency Through Time based Coding

ECCV 2020

citations

Samples With Low Loss Curvature Improve Data Efficiency

CVPR 2023

citations

Kaushik Roy

papers (16)

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

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

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

Memorization Through the Lens of Curvature of Loss Function Around Samples

Event-based Temporally Dense Optical Flow Estimation with Sequential Learning

Global Update Tracking: A Decentralized Learning Algorithm for Heterogeneous Data

Unveiling Privacy, Memorization, and Input Curvature Links

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

DCT-CryptoNets: Scaling Private Inference in the Frequency Domain

PIXELS: Progressive Image Xemplar-based Editing with Latent Surgery

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

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

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

Deep Spiking Neural Network: Energy Efficiency Through Time based Coding

Samples With Low Loss Curvature Improve Data Efficiency

papers (16)

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

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

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

Memorization Through the Lens of Curvature of Loss Function Around Samples

Event-based Temporally Dense Optical Flow Estimation with Sequential Learning

Global Update Tracking: A Decentralized Learning Algorithm for Heterogeneous Data

Unveiling Privacy, Memorization, and Input Curvature Links

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

DCT-CryptoNets: Scaling Private Inference in the Frequency Domain

PIXELS: Progressive Image Xemplar-based Editing with Latent Surgery

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

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

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

Deep Spiking Neural Network: Energy Efficiency Through Time based Coding

Samples With Low Loss Curvature Improve Data Efficiency