Background Invariant Classification on Infrared Imagery by Data Efficient Training and Reducing Bias in CNNs

01/22/2022
by   Maliha Arif, et al.
18

Even though convolutional neural networks can classify objects in images very accurately, it is well known that the attention of the network may not always be on the semantically important regions of the scene. It has been observed that networks often learn background textures which are not relevant to the object of interest. In turn this makes the networks susceptible to variations and changes in the background which negatively affect their performance. We propose a new two-step training procedure called split training to reduce this bias in CNNs on both Infrared imagery and RGB data. Our split training procedure has two steps: using MSE loss first train the layers of the network on images with background to match the activations of the same network when it is trained using images without background; then with these layers frozen, train the rest of the network with cross-entropy loss to classify the objects. Our training method outperforms the traditional training procedure in both a simple CNN architecture, and deep CNNs like VGG and Densenet which use lots of hardware resources, and learns to mimic human vision which focuses more on shape and structure than background with higher accuracy.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 6

page 7

research
03/21/2018

Assessing Shape Bias Property of Convolutional Neural Networks

It is known that humans display "shape bias" when classifying new items,...
research
11/05/2019

Detecting and Tracking Small Moving Objects in Wide Area Motion Imagery (WAMI) Using Convolutional Neural Networks (CNNs)

This paper proposes an approach to detect moving objects in Wide Area Mo...
research
05/22/2022

CNNs are Myopic

We claim that Convolutional Neural Networks (CNNs) learn to classify ima...
research
10/08/2018

Bootstrapped CNNs for Building Segmentation on RGB-D Aerial Imagery

Detection of buildings and other objects from aerial images has various ...
research
03/20/2017

On the Limitation of Convolutional Neural Networks in Recognizing Negative Images

Convolutional Neural Networks (CNNs) have achieved state-of-the-art perf...
research
01/17/2019

Background subtraction on depth videos with convolutional neural networks

Background subtraction is a significant component of computer vision sys...
research
01/17/2022

H E-adversarial network: a convolutional neural network to learn stain-invariant features through Hematoxylin Eosin regression

Computational pathology is a domain that aims to develop algorithms to a...

Please sign up or login with your details

Forgot password? Click here to reset