Domain adaptive object detection

We study the use of domain adaptation and transfer learning techniques as part of a framework for adaptive ob-ject detection. Unlike recent applications of domain adap-tation work in computer vision, which generally focus on image classification, we explore the problem of extreme class imbalance present when performing domain adapta-tion for object detection. The main difficulty caused by this imbalance is that test images contain millions or billions of negative image subwindows but just a few image subwin-dows containing positive instances, which makes it difficult to adapt to changes in the positive classes present new do-mains by simple techniques such as random sampling. We propose an initial approach to addressing this problem and apply our technique to vehicle detection in a challenging urban surveillance dataset, demonstrating the performance of our approach with various amounts of supervision, in-cluding the fully unsupervised case. 1