Penalizing Top Performers: Conservative Loss for Semantic Segmentation Adaptation

Abstract

Due to the expensive and time-consuming annotations (e.g., segmentation) for real-world images, recent works in computer vision resort to synthetic data. However, the performance on the real image often drops significantly because of the domain shift between the synthetic data and the real images. In this setting, domain adaptation brings an appealing option. The effective approaches of domain adaptation shape the representations that (1) are discriminative for the main task and (2) have good generalization capability for domain shift. To this end, we propose a novel loss function, i.e., Conservative Loss, which penalizes the extreme good and bad cases while encouraging the moderate examples. More specifically, it enables the network to learn features that are discriminative by gradient descent and are invariant to the change of domains via gradient ascend method. Extensive experiments on synthetic to real segmentation adaptation show our proposed method achieves state of the art results. Ablation studies give more insights into properties of the Conservative Loss. Exploratory experiments and discussion demonstrate that our Conservative Loss has good flexibility rather than restricting an exact form.

arXiv commentECCV 2018

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Learning Transferable Features with Deep Adaptation Networks
• SGDR: Stochastic Gradient Descent with Warm Restarts
• Energy-based Generative Adversarial Network
• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes
• Domain Adaptation: Learning Bounds and Algorithms
• Domain-Adversarial Neural Networks
• Wider or Deeper: Revisiting the ResNet Model for Visual Recognition

Cited by in corpus (6)

• Harmonizing Transferability and Discriminability for Adapting Object Detectors
• All about Structure: Adapting Structural Information across Domains for Boosting Semantic Segmentation
• Label-Driven Reconstruction for Domain Adaptation in Semantic Segmentation
• Semi-supervised Domain Adaptation based on Dual-level Domain Mixing for Semantic Segmentation
• Transferring and Regularizing Prediction for Semantic Segmentation
• DLOW: Domain Flow for Adaptation and Generalization