Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector
This addresses the challenge of adapting object detectors to unseen domains with variations in appearance, viewpoints, or backgrounds, offering a novel approach to reduce foreground/background confusion and background noise.
The paper tackles the problem of domain adaptation for object detectors by proposing a center-aware feature alignment method that focuses on foreground pixels, achieving improved performance across various adaptation settings compared to existing state-of-the-art algorithms.
A domain adaptive object detector aims to adapt itself to unseen domains that may contain variations of object appearance, viewpoints or backgrounds. Most existing methods adopt feature alignment either on the image level or instance level. However, image-level alignment on global features may tangle foreground/background pixels at the same time, while instance-level alignment using proposals may suffer from the background noise. Different from existing solutions, we propose a domain adaptation framework that accounts for each pixel via predicting pixel-wise objectness and centerness. Specifically, the proposed method carries out center-aware alignment by paying more attention to foreground pixels, hence achieving better adaptation across domains. We demonstrate our method on numerous adaptation settings with extensive experimental results and show favorable performance against existing state-of-the-art algorithms.