Reducing the feature divergence of RGB and near-infrared images using Switchable Normalization
arXiv:2106.03088
Abstract
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.
arXiv commentCVPR2020 AgriVision workshop
References in corpus (10)
- Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
- Deep Residual Learning for Image Recognition
- Instance Normalization: The Missing Ingredient for Fast Stylization
- Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
- The Cityscapes Dataset for Semantic Urban Scene Understanding
- Revisiting Batch Normalization For Practical Domain Adaptation
- Semantic Understanding of Scenes through the ADE20K Dataset
- Differentiable Learning-to-Normalize via Switchable Normalization
- The Lovász-Softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks
- Agriculture-Vision: A Large Aerial Image Database for Agricultural Pattern Analysis