# Strong-Weak Distribution Alignment for Adaptive Object Detection

## TL;DR

This paper introduces a novel unsupervised domain adaptation method for object detection that combines strong local feature alignment with weak global image alignment, effectively handling domain shifts with different scene layouts.

## Contribution

The paper proposes a weak global alignment model that focuses on globally similar images and a strong local alignment model for feature-level matching, advancing domain adaptation techniques for object detection.

## Key findings

- Effective on four diverse datasets with various domain shifts.
- Outperforms existing methods in unsupervised object detection adaptation.
- Code is publicly available for reproducibility.

## Abstract

We propose an approach for unsupervised adaptation of object detectors from label-rich to label-poor domains which can significantly reduce annotation costs associated with detection. Recently, approaches that align distributions of source and target images using an adversarial loss have been proven effective for adapting object classifiers. However, for object detection, fully matching the entire distributions of source and target images to each other at the global image level may fail, as domains could have distinct scene layouts and different combinations of objects. On the other hand, strong matching of local features such as texture and color makes sense, as it does not change category level semantics. This motivates us to propose a novel method for detector adaptation based on strong local alignment and weak global alignment. Our key contribution is the weak alignment model, which focuses the adversarial alignment loss on images that are globally similar and puts less emphasis on aligning images that are globally dissimilar. Additionally, we design the strong domain alignment model to only look at local receptive fields of the feature map. We empirically verify the effectiveness of our method on four datasets comprising both large and small domain shifts. Our code is available at \url{https://github.com/VisionLearningGroup/DA_Detection}