Adaptive Object Detection with Dual Multi-Label Prediction

european conference on computer vision, pp. 54-69, 2020.

Cited by: 0|Bibtex|Views43
Other Links: arxiv.org|academic.microsoft.com

Abstract:

In this paper, we propose a novel end-to-end unsupervised deep domain adaptation model for adaptive object detection by exploiting multi-label object recognition as a dual auxiliary task. The model exploits multi-label prediction to reveal the object category information in each image and then uses the prediction results to perform condit...More

Code:

Data:

Your rating :
0

 

Tags
Comments