Label-Driven Reconstruction for Domain Adaptation in Semantic Segmentation

Abstract

Unsupervised domain adaptation enables to alleviate the need for pixel-wise annotation in the semantic segmentation. One of the most common strategies is to translate images from the source domain to the target domain and then align their marginal distributions in the feature space using adversarial learning. However, source-to-target translation enlarges the bias in translated images and introduces extra computations, owing to the dominant data size of the source domain. Furthermore, consistency of the joint distribution in source and target domains cannot be guaranteed through global feature alignment. Here, we present an innovative framework, designed to mitigate the image translation bias and align cross-domain features with the same category. This is achieved by 1) performing the target-to-source translation and 2) reconstructing both source and target images from their predicted labels. Extensive experiments on adapting from synthetic to real urban scene understanding demonstrate that our framework competes favorably against existing state-of-the-art methods.

ECCV 2020

References in corpus (19)

• Adam: A Method for Stochastic Optimization
• Deep Residual Learning for Image Recognition
• Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
• Learning Transferable Features with Deep Adaptation Networks
• Unsupervised Domain Adaptation by Backpropagation
• Deep Domain Confusion: Maximizing for Domain Invariance
• NIPS 2016 Tutorial: Generative Adversarial Networks
• Fully Convolutional Networks for Semantic Segmentation
• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• Unsupervised Image-to-Image Translation Networks
• Adversarial Discriminative Domain Adaptation
• Searching for Efficient Multi-Scale Architectures for Dense Image Prediction
• Pyramid Scene Parsing Network
• High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
• Semantic Image Segmentation via Deep Parsing Network
• BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
• Fully Convolutional Adaptation Networks for Semantic Segmentation
• Penalizing Top Performers: Conservative Loss for Semantic Segmentation Adaptation
• From Image-level to Pixel-level Labeling with Convolutional Networks

Cited by in corpus (5)

• Improving Semantic Segmentation via Self-Training
• Unsupervised Domain Adaptation in Semantic Segmentation: a Review
• Unsupervised Domain Adaptation for Semantic Segmentation via Low-level Edge Information Transfer
• Joint Semi-supervised 3D Super-Resolution and Segmentation with Mixed Adversarial Gaussian Domain Adaptation
• Exploiting Inter-pixel Correlations in Unsupervised Domain Adaptation for Semantic Segmentation