Search Results for author: Che-Rung Lee

Found 5 papers, 2 papers with code

Overload: Latency Attacks on Object Detection for Edge Devices

no code implementations11 Apr 2023 Erh-Chung Chen, Pin-Yu Chen, I-Hsin Chung, Che-Rung Lee

Our method is based on a newly formulated optimization problem and a novel technique, called spatial attention, to increase the inference time of object detection.

Object object-detection +1

Low-rank Tensor Decomposition for Compression of Convolutional Neural Networks Using Funnel Regularization

no code implementations7 Dec 2021 Bo-Shiuan Chu, Che-Rung Lee

Tensor decomposition is one of the fundamental technique for model compression of deep convolution neural networks owing to its ability to reveal the latent relations among complex structures.

Model Compression Tensor Decomposition

LTD: Low Temperature Distillation for Robust Adversarial Training

1 code implementation3 Nov 2021 Erh-Chung Chen, Che-Rung Lee

Despite the popularity of neural network models, a significant gap exists between the natural and robust accuracy of these models.

Knowledge Distillation

Knowledge Distillation with Feature Maps for Image Classification

no code implementations3 Dec 2018 Wei-Chun Chen, Chia-Che Chang, Chien-Yu Lu, Che-Rung Lee

One promising method is knowledge distillation (KD), which creates a fast-to-execute student model to mimic a large teacher network.

Classification General Classification +3

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