2 papers
cs.LG2022
Mixup for Test-Time Training
Bochao Zhang, Rui Shao, Jingda Du +1
Test-time training provides a new approach solving the problem of domain shift. In its framework, a test-time training phase is inserted between training phase and test phase. Duri…
cs.CV2020
Deep Active Learning for Remote Sensing Object Detection
Zhenshen Qu, Jingda Du, Yong Cao +2
Recently, CNN object detectors have achieved high accuracy on remote sensing images but require huge labor and time costs on annotation. In this paper, we propose a new uncertainty…