DeepCorrect: Correcting DNN models against Image Distortions

05/05/2017
by   Tejas Borkar, et al.
0

In recent years, the widespread use of deep neural networks (DNNs) has facilitated great improvements in performance for computer vision tasks like image classification and object recognition. In most realistic computer vision applications, an input image undergoes some form of image distortion such as blur and additive noise during image acquisition or transmission. Deep networks trained on pristine images perform poorly when tested on distorted images affected by image blur or additive noise. In this paper, we evaluate the effect of image distortions like Gaussian blur and additive noise on the outputs of pre-trained convolutional filters. We propose a metric to identify the most noise susceptible convolutional filters and rank them in order of the highest gain in classification accuracy upon correction. In our proposed approach called DeepCorrect, we apply small convolutional filter blocks on top of these ranked filters and train them to correct the worst noise and blur affected filter outputs. Applying DeepCorrect on the CIFAR-100 dataset, we significantly improve the robustness of DNNs against distorted images and also outperform the alternative approach of fine-tuning networks.

READ FULL TEXT
research
01/08/2017

On Classification of Distorted Images with Deep Convolutional Neural Networks

Image blur and image noise are common distortions during image acquisiti...
research
08/29/2023

Classification robustness to common optical aberrations

Computer vision using deep neural networks (DNNs) has brought about semi...
research
11/17/2016

Examining the Impact of Blur on Recognition by Convolutional Networks

State-of-the-art algorithms for many semantic visual tasks are based on ...
research
11/14/2018

Distortion Robust Image Classification with Deep Convolutional Neural Network based on Discrete Cosine Transform

State of the art CNN models for image classification are found to be hig...
research
10/18/2017

Enhancing the Performance of Convolutional Neural Networks on Quality Degraded Datasets

Despite the appeal of deep neural networks that largely replace the trad...
research
06/02/2017

Dynamic Steerable Blocks in Deep Residual Networks

Filters in convolutional networks are typically parameterized in a pixel...
research
11/14/2018

Distortion Robust Image Classification using Deep Convolutional Neural Network with Discrete Cosine Transform

Convolutional Neural Network is good at image classification. However, i...

Please sign up or login with your details

Forgot password? Click here to reset