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

arXiv: https://arxiv.org/abs/2201.09144 · HTML: https://mlsanity.com/paper/2201.09144/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 12 references that are in the map.
- First posted on arXiv 22 Jan 2022.

## Builds on (most cited first, 9 of 9)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Noise or Signal: The Role of Image Backgrounds in Object Recognition](https://mlsanity.com/paper/2006.09994/) (2020)
- [Dual Path Networks](https://mlsanity.com/paper/1707.01629/) (2017)
- [Object Recognition with and without Objects](https://mlsanity.com/paper/1611.06596/) (2016)
- [Time for a Background Check! Uncovering the impact of Background Features on Deep Neural Networks](https://mlsanity.com/paper/2006.14077/) (2020)

## Abstract (arXiv)

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.