Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector
arXiv:2008.08574
Abstract
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.
Accepted in ECCV'20. Project page: https://chengchunhsu.github.io/EveryPixelMatters/
References in corpus (7)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Learning Transferable Features with Deep Adaptation Networks
- Semantic Foggy Scene Understanding with Synthetic Data
- T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos
- Image Captioning and Visual Question Answering Based on Attributes and External Knowledge
- Adaptation Across Extreme Variations using Unlabeled Domain Bridges