Online Continual Domain Adaptation for Semantic Image Segmentation Using Internal Representations
This addresses the need for maintaining segmentation performance in dynamic environments without requiring source data access during adaptation, though it is incremental as it builds on existing UDA approaches.
The paper tackles the problem of semantic segmentation models failing to generalize when data distributions change over time, by developing an online unsupervised domain adaptation algorithm that minimizes distributional distance between source and target latent features, achieving favorable performance compared to state-of-the-art methods on established datasets.
Semantic segmentation models trained on annotated data fail to generalize well when the input data distribution changes over extended time period, leading to requiring re-training to maintain performance. Classic Unsupervised domain adaptation (UDA) attempts to address a similar problem when there is target domain with no annotated data points through transferring knowledge from a source domain with annotated data. We develop an online UDA algorithm for semantic segmentation of images that improves model generalization on unannotated domains in scenarios where source data access is restricted during adaptation. We perform model adaptation is by minimizing the distributional distance between the source latent features and the target features in a shared embedding space. Our solution promotes a shared domain-agnostic latent feature space between the two domains, which allows for classifier generalization on the target dataset. To alleviate the need of access to source samples during adaptation, we approximate the source latent feature distribution via an appropriate surrogate distribution, in this case a Gassian mixture model (GMM). We evaluate our approach on well established semantic segmentation datasets and demonstrate it compares favorably against state-of-the-art (SOTA) UDA semantic segmentation methods.