Rethinking Ensemble-Distillation for Semantic Segmentation Based Unsupervised Domain Adaptation

National Tsing Hua University
Keywords:
Unsupervised Domain Adaptation
Semantic Segmentation
Ensemble-Distillation

Venue:
IEEE/CVF Computer Vision and Pattern Recognition Conference Workshop (CVPRW 2021)
Journal Extension:
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

Abstract

Recent researches on unsupervised domain adaptation (UDA) have demonstrated that end-to-end ensemble learning frameworks serve as a compelling option for UDA tasks. Nevertheless, these end-to-end ensemble learning methods often lack flexibility as any modification to the ensemble requires retraining of their frameworks. To address this problem, we propose a flexible ensemble-distillation framework for performing semantic segmentation based UDA, allowing any arbitrary composition of the members in the ensemble while still maintaining its superior performance. To achieve such flexibility, our framework is designed to be robust against the output inconsistency and the performance variation of the members within the ensemble. To examine the effectiveness and the robustness of our method, we perform an extensive set of experiments on both GTA5 to Cityscapes and SYNTHIA to Cityscapes benchmarks to quantitatively inspect the improvements achievable by our method. We further provide detailed analyses to validate that our design choices are practical and beneficial. The experimental evidence validates that the proposed method indeed offer superior performance, robustness and flexibility in semantic segmentation based UDA tasks against contemporary baseline methods.

Video


Poster

BibTeX

@InProceedings{Chao_2021_CVPR,
    author    = {Chao, Chen-Hao and Cheng, Bo-Wun and Lee, Chun-Yi},
    title     = {Rethinking Ensemble-Distillation for Semantic Segmentation Based Unsupervised Domain Adaption},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
    month     = {June},
    year      = {2021},
    pages     = {2610-2620}
}