25 citations · 42 across the 3 of their papers we have counts for
3 papers · 1 filter
Anti-aliasing Deep Image Classifiers using Novel Depth Adaptive Blurring and Activation Function
Md Tahmid Hossain, Shyh Wei Teng, Ferdous Sohel +1
Deep convolutional networks are vulnerable to image translation or shift, partly due to common down-sampling layers, e.g., max-pooling and strided convolution. These operations vio…
Robust Image Classification Using A Low-Pass Activation Function and DCT Augmentation
Md Tahmid Hossain, Shyh Wei Teng, Ferdous Sohel +1
Convolutional Neural Network's (CNN's) performance disparity on clean and corrupted datasets has recently come under scrutiny. In this work, we analyse common corruptions in the fr…
Distortion Robust Image Classification using Deep Convolutional Neural Network with Discrete Cosine Transform
Md Tahmid Hossain, Shyh Wei Teng, Dengsheng Zhang +2
Convolutional Neural Network is good at image classification. However, it is found to be vulnerable to image quality degradation. Even a small amount of distortion such as noise or…