Rethinking Ensemble-Distillation for Semantic Segmentation Based Unsupervised Domain Adaptation

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→Cityscapes and SYNTHIA→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.

Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Driving

“…Other architectures that were used in UDA works are the MobileNetv2 as a backbone [43], [44], DRN-26 [45], [46], [47], DRN-105 [48], and smaller versions of the ResNet like ResNet-18 [49], ResNet-38 [50], [51], [52] and ResNet-50 [53], [54]. However, all these architectures appear only rarely in UDA research.…”