ADAS: A Direct Adaptation Strategy for Multi-Target Domain Adaptive Semantic Segmentation
This addresses the problem of adapting semantic segmentation models to multiple target domains efficiently, which is incremental as it builds on existing domain adaptation methods.
The paper tackles multi-target domain adaptation for semantic segmentation by introducing ADAS, a direct adaptation strategy that uses a multi-target domain transfer network and bi-directional adaptive region selection to achieve state-of-the-art performance without pretrained domain-specific models.
In this paper, we present a direct adaptation strategy (ADAS), which aims to directly adapt a single model to multiple target domains in a semantic segmentation task without pretrained domain-specific models. To do so, we design a multi-target domain transfer network (MTDT-Net) that aligns visual attributes across domains by transferring the domain distinctive features through a new target adaptive denormalization (TAD) module. Moreover, we propose a bi-directional adaptive region selection (BARS) that reduces the attribute ambiguity among the class labels by adaptively selecting the regions with consistent feature statistics. We show that our single MTDT-Net can synthesize visually pleasing domain transferred images with complex driving datasets, and BARS effectively filters out the unnecessary region of training images for each target domain. With the collaboration of MTDT-Net and BARS, our ADAS achieves state-of-the-art performance for multi-target domain adaptation (MTDA). To the best of our knowledge, our method is the first MTDA method that directly adapts to multiple domains in semantic segmentation.