Rethinking Ensemble-Distillation for Semantic Segmentation Based Unsupervised Domain Adaptation
This work addresses a flexibility issue in ensemble methods for domain adaptation in semantic segmentation, which is incremental as it builds on existing ensemble-distillation approaches.
The paper tackled the lack of flexibility in ensemble learning for unsupervised domain adaptation in semantic segmentation by proposing a flexible ensemble-distillation framework that allows arbitrary composition of ensemble members without retraining, achieving superior performance on benchmarks like GTA5 to Cityscapes and SYNTHIA to Cityscapes.
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.