Collaborative Training between Region Proposal Localization and Classification for Domain Adaptive Object Detection

by   Ganlong Zhao, et al.

Object detectors are usually trained with large amount of labeled data, which is expensive and labor-intensive. Pre-trained detectors applied to unlabeled dataset always suffer from the difference of dataset distribution, also called domain shift. Domain adaptation for object detection tries to adapt the detector from labeled datasets to unlabeled ones for better performance. In this paper, we are the first to reveal that the region proposal network (RPN) and region proposal classifier (RPC) in the endemic two-stage detectors (e.g., Faster RCNN) demonstrate significantly different transferability when facing large domain gap. The region classifier shows preferable performance but is limited without RPN's high-quality proposals while simple alignment in the backbone network is not effective enough for RPN adaptation. We delve into the consistency and the difference of RPN and RPC, treat them individually and leverage high-confidence output of one as mutual guidance to train the other. Moreover, the samples with low-confidence are used for discrepancy calculation between RPN and RPC and minimax optimization. Extensive experimental results on various scenarios have demonstrated the effectiveness of our proposed method in both domain-adaptive region proposal generation and object detection. Code is available at



There are no comments yet.


page 2

page 7

page 13


Oriented R-CNN for Object Detection

Current state-of-the-art two-stage detectors generate oriented proposals...

Task-specific Inconsistency Alignment for Domain Adaptive Object Detection

Detectors trained with massive labeled data often exhibit dramatic perfo...

Exploring Categorical Regularization for Domain Adaptive Object Detection

In this paper, we tackle the domain adaptive object detection problem, w...

Attention-based Domain Adaptation for Single Stage Detectors

While domain adaptation has been used to improve the performance of obje...

Mixup Regularization for Region Proposal based Object Detectors

Mixup - a neural network regularization technique based on linear interp...

Reference-based Defect Detection Network

The defect detection task can be regarded as a realistic scenario of obj...

YOLO – You only look 10647 times

With this work we are explaining the "You Only Look Once" (YOLO) single-...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.