3 papers
cs.CV2019
Bias-Aware Heapified Policy for Active Learning
Wen-Yen Chang, Wen-Huan Chiang, Shao-Hao Lu +2
The data efficiency of learning-based algorithms is more and more important since high-quality and clean data is expensive as well as hard to collect. In order to achieve high mode…
cs.CV2018
Leveraging Motion Priors in Videos for Improving Human Segmentation
Yu-Ting Chen, Wen-Yen Chang, Hai-Lun Lu +2
Despite many advances in deep-learning based semantic segmentation, performance drop due to distribution mismatch is often encountered in the real world. Recently, a few domain ada…
cs.CV2018
Efficient Uncertainty Estimation for Semantic Segmentation in Videos
Po-Yu Huang, Wan-Ting Hsu, Chun-Yueh Chiu +2
Uncertainty estimation in deep learning becomes more important recently. A deep learning model can't be applied in real applications if we don't know whether the model is certain a…