RPN Prototype Alignment For Domain Adaptive Object Detector
Authors:
- 1 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 12420-12429
Abstract
Recent years have witnessed great progress of object detection. However, due to the domain shift problem, applying the knowledge of an object detector learned from one specific domain to another one often suffers severe performance degradation. Most existing methods adopt feature alignment either on the backbone network or instance classifier to increase the transferability of object detector. Differently, we propose to perform feature alignment in the RPN stage such that the foreground and background RPN proposals in target domain can be effectively distinguished. Specifically, we first construct one set of learnable RPN prototpyes, and then enforce the RPN features to align with the prototypes for both source and target domains. It essentially cooperates the learning of RPN prototypes and features to align the source and target RPN features. Particularly, we propose a simple yet effective method suitable for RPN feature alignment to generate high-quality pseudo label of proposals in target domain, i.e., using the filtered detection results with IoU. Furthermore, we adopt Grad CAM to find the discriminative region within a foreground proposal and use it to increase the discriminability of RPN features for alignment. We conduct extensive experiments on multiple cross-domain detection scenarios, and the results show the effectiveness of our proposed method against previous state-of-the-art methods.Keywords
Funding Information
- National Natural Science Foundation of China
- Youth Innovation Promotion Association
This publication has 43 references indexed in Scilit:
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- You Only Look Once: Unified, Real-Time Object Detection2016
- Fast R-CNN2015
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- Incremental Domain Adaptation of Deformable Part-based Models2014
- Domain adaptive object detection2013
- Unbiased look at dataset bias2011
- A theory of learning from different domainsMachine Learning, 2009
- Rapid object detection using a boosted cascade of simple features2005
- Histograms of Oriented Gradients for Human Detection2005