# Reducing the feature divergence of RGB and near-infrared images using Switchable Normalization

arXiv: https://arxiv.org/abs/2106.03088 · HTML: https://mlsanity.com/paper/2106.03088/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 21 references that are in the map.
- First posted on arXiv 6 Jun 2021.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net](https://mlsanity.com/paper/1807.09441/) (2018)
- [Revisiting Batch Normalization For Practical Domain Adaptation](https://mlsanity.com/paper/1603.04779/) (2016)
- [Agriculture-Vision: A Large Aerial Image Database for Agricultural Pattern Analysis](https://mlsanity.com/paper/2001.01306/) (2020)
- [Differentiable Learning-to-Normalize via Switchable Normalization](https://mlsanity.com/paper/1806.10779/) (2018)

## Built on by (most cited first, 5 of 5)

- [Augmentation Invariance and Adaptive Sampling in Semantic Segmentation of Agricultural Aerial Images](https://mlsanity.com/paper/2204.07969/) (2022)
- [HalluciDet: Hallucinating RGB Modality for Person Detection Through Privileged Information](https://mlsanity.com/paper/2310.04662/) (2023)
- [A Contrastive Distillation Approach for Incremental Semantic Segmentation in Aerial Images](https://mlsanity.com/paper/2112.03814/) (2021)
- [Rail-5k: a Real-World Dataset for Rail Surface Defects Detection](https://mlsanity.com/paper/2106.14366/) (2021)
- [Dual Atrous Separable Convolution for Improving Agricultural Semantic Segmentation](https://mlsanity.com/paper/2506.22570/) (2025)

## Abstract (arXiv)

Visual pattern recognition over agricultural areas is an important application of aerial image processing. In this paper, we consider the multi-modality nature of agricultural aerial images and show that naively combining different modalities together without taking the feature divergence into account can lead to sub-optimal results. Thus, we apply a Switchable Normalization block to our DeepLabV3 segmentation model to alleviate the feature divergence. Using the popular symmetric Kullback Leibler divergence measure, we show that our model can greatly reduce the divergence between RGB and near-infrared channels. Together with a hybrid loss function, our model achieves nearly 10% improvements in mean IoU over previously published baseline.