Continual Domain Adaptation on Aerial Images under Gradually Degrading Weather

TL;DR

This paper introduces benchmark datasets simulating gradually worsening weather conditions for aerial imagery, evaluates continual domain adaptation models under realistic constraints, and proposes gradient normalization to improve stability.

Contribution

It creates new benchmarks for continual domain adaptation under degrading weather, compares different architectures, and offers a simple stability improvement method.

Findings

Buffer-fed continual DA models face stability issues.

Gradient normalization improves training stability.

Transformer models show different adaptation behaviors.

Abstract

Domain adaptation (DA) strives to mitigate the domain gap between the source domain where a model is trained, and the target domain where the model is deployed. When a deep learning model is deployed on an aerial platform, it may face gradually degrading weather conditions during operation, leading to widening domain gaps between the training data and the encountered evaluation data. We synthesize two such gradually worsening weather conditions on real images from two existing aerial imagery datasets, generating a total of four benchmark datasets. Under the continual, or test-time adaptation setting, we evaluate three DA models on our datasets: a baseline standard DA model and two continual DA models. In such setting, the models can access only one small portion, or one batch of the target data at a time, and adaptation takes place continually, and over only one epoch of the data. The combination of the constraints of continual adaptation, and gradually deteriorating weather conditions provide the practical DA scenario for aerial deployment. Among the evaluated models, we consider both convolutional and transformer architectures for comparison. We discover stability issues during adaptation for existing buffer-fed continual DA methods, and offer gradient normalization as a simple solution to curb training instability.