Transferring and Regularizing Prediction for Semantic Segmentation

Abstract

Semantic segmentation often requires a large set of images with pixel-level annotations. In the view of extremely expensive expert labeling, recent research has shown that the models trained on photo-realistic synthetic data (e.g., computer games) with computer-generated annotations can be adapted to real images. Despite this progress, without constraining the prediction on real images, the models will easily overfit on synthetic data due to severe domain mismatch. In this paper, we novelly exploit the intrinsic properties of semantic segmentation to alleviate such problem for model transfer. Specifically, we present a Regularizer of Prediction Transfer (RPT) that imposes the intrinsic properties as constraints to regularize model transfer in an unsupervised fashion. These constraints include patch-level, cluster-level and context-level semantic prediction consistencies at different levels of image formation. As the transfer is label-free and data-driven, the robustness of prediction is addressed by selectively involving a subset of image regions for model regularization. Extensive experiments are conducted to verify the proposal of RPT on the transfer of models trained on GTA5 and SYNTHIA (synthetic data) to Cityscapes dataset (urban street scenes). RPT shows consistent improvements when injecting the constraints on several neural networks for semantic segmentation. More remarkably, when integrating RPT into the adversarial-based segmentation framework, we report to-date the best results: mIoU of 53.2%/51.7% when transferring from GTA5/SYNTHIA to Cityscapes, respectively.

arXiv commentCVPR 2020

References in corpus (15)

• Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
• Caffe: Convolutional Architecture for Fast Feature Embedding
• ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• Searching for Efficient Multi-Scale Architectures for Dense Image Prediction
• BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
• Domain Stylization: A Strong, Simple Baseline for Synthetic to Real Image Domain Adaptation
• Fully Convolutional Adaptation Networks for Semantic Segmentation
• Transferrable Prototypical Networks for Unsupervised Domain Adaptation
• Domain Adaptation for Semantic Segmentation with Maximum Squares Loss
• Effective Use of Synthetic Data for Urban Scene Semantic Segmentation
• All about Structure: Adapting Structural Information across Domains for Boosting Semantic Segmentation
• Penalizing Top Performers: Conservative Loss for Semantic Segmentation Adaptation
• Customizable Architecture Search for Semantic Segmentation