Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentation

TL;DR

This paper introduces AdaBoost Student, an adaptive boosting approach for domain adaptation in scene segmentation that eliminates the need for early stopping and enhances robustness by combining models during training.

Contribution

The paper proposes a novel bootstrapping method, AdaBoost Student, which integrates adaptive boosting with deep learning for domain adaptation, removing the reliance on early stopping.

Findings

Achieves competitive results on scene segmentation benchmarks.

Provides a robust training method independent of early stopping.

Can be combined with existing domain adaptation techniques for improved performance.

Abstract

Domain adaptation is to transfer the shared knowledge learned from the source domain to a new environment, i.e., target domain. One common practice is to train the model on both labeled source-domain data and unlabeled target-domain data. Yet the learned models are usually biased due to the strong supervision of the source domain. Most researchers adopt the early-stopping strategy to prevent over-fitting, but when to stop training remains a challenging problem since the lack of the target-domain validation set. In this paper, we propose one efficient bootstrapping method, called Adaboost Student, explicitly learning complementary models during training and liberating users from empirical early stopping. Adaboost Student combines the deep model learning with the conventional training strategy, i.e., adaptive boosting, and enables interactions between learned models and the data sampler. We adopt one adaptive data sampler to progressively facilitate learning on hard samples and aggregate "weak" models to prevent over-fitting. Extensive experiments show that (1) Without the need to worry about the stopping time, AdaBoost Student provides one robust solution by efficient complementary model learning during training. (2) AdaBoost Student is orthogonal to most domain adaptation methods, which can be combined with existing approaches to further improve the state-of-the-art performance. We have achieved competitive results on three widely-used scene segmentation domain adaptation benchmarks.