ColorMapGAN: Unsupervised Domain Adaptation for Semantic Segmentation Using Color Mapping Generative Adversarial Networks

Abstract

Due to the various reasons such as atmospheric effects and differences in acquisition, it is often the case that there exists a large difference between spectral bands of satellite images collected from different geographic locations. The large shift between spectral distributions of training and test data causes the current state of the art supervised learning approaches to output unsatisfactory maps. We present a novel semantic segmentation framework that is robust to such shift. The key component of the proposed framework is Color Mapping Generative Adversarial Networks (ColorMapGAN), which can generate fake training images that are semantically exactly the same as training images, but whose spectral distribution is similar to the distribution of the test images. We then use the fake images and the ground-truth for the training images to fine-tune the already trained classifier. Contrary to the existing Generative Adversarial Networks (GANs), the generator in ColorMapGAN does not have any convolutional or pooling layers. It learns to transform the colors of the training data to the colors of the test data by performing only one element-wise matrix multiplication and one matrix addition operations. Thanks to the architecturally simple but powerful design of ColorMapGAN, the proposed framework outperforms the existing approaches with a large margin in terms of both accuracy and computational complexity.

References in corpus (10)

• Conditional Generative Adversarial Nets
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Instance Normalization: The Missing Ingredient for Fast Stylization
• Empirical Evaluation of Rectified Activations in Convolutional Network
• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• Texture Networks: Feed-forward Synthesis of Textures and Stylized Images
• TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation
• Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes
• Incremental Learning for Semantic Segmentation of Large-Scale Remote Sensing Data
• Preserving Color in Neural Artistic Style Transfer

Cited by in corpus (6)

• DAugNet: Unsupervised, Multi-source, Multi-target, and Life-long Domain Adaptation for Semantic Segmentation of Satellite Images
• AOL: Adaptive Online Learning for Human Trajectory Prediction in Dynamic Video Scenes
• Randomized Histogram Matching: A Simple Augmentation for Unsupervised Domain Adaptation in Overhead Imagery
• Cross-Sensor Adversarial Domain Adaptation of Landsat-8 and Proba-V images for Cloud Detection
• Multi-Feature Fusion-based Scene Classification Framework for HSR Images
• EvoGAN: An Evolutionary Computation Assisted GAN