Unsupervised Domain Adaptive Detection with Network Stability Analysis

TL;DR

This paper introduces a novel Network Stability Analysis framework for unsupervised domain adaptive detection, leveraging stability concepts to improve detector generality across different domains, achieving state-of-the-art results.

Contribution

The paper proposes a new NSA framework that considers various disturbances for domain adaptation, applicable to multiple detection models, and achieves superior performance on benchmark datasets.

Findings

Achieved 52.7% mAP on Cityscapes-to-FoggyCityscapes.

NSA improves domain adaptation by analyzing external and internal consistency.

Applicable to both two-stage and one-stage detection models.

Abstract

Domain adaptive detection aims to improve the generality of a detector, learned from the labeled source domain, on the unlabeled target domain. In this work, drawing inspiration from the concept of stability from the control theory that a robust system requires to remain consistent both externally and internally regardless of disturbances, we propose a novel framework that achieves unsupervised domain adaptive detection through stability analysis. In specific, we treat discrepancies between images and regions from different domains as disturbances, and introduce a novel simple but effective Network Stability Analysis (NSA) framework that considers various disturbances for domain adaptation. Particularly, we explore three types of perturbations including heavy and light image-level disturbances and instancelevel disturbance. For each type, NSA performs external consistency analysis on the outputs from raw and perturbed images and/or internal consistency analysis on their features, using teacher-student models. By integrating NSA into Faster R-CNN, we immediately achieve state-of-the-art results. In particular, we set a new record of 52.7% mAP on Cityscapes-to-FoggyCityscapes, showing the potential of NSA for domain adaptive detection. It is worth noticing, our NSA is designed for general purpose, and thus applicable to one-stage detection model (e.g., FCOS) besides the adopted one, as shown by experiments. https://github.com/tiankongzhang/NSA.