Unsupervised domain adaptation (UDA) in semantic segmentation is a fundamental yet promising task relieving the need for laborious annotation works.
no code implementations • 8 Oct 2019 • José Ignacio Orlando, Huazhu Fu, João Barbossa Breda, Karel van Keer, Deepti. R. Bathula, Andrés Diaz-Pinto, Ruogu Fang, Pheng-Ann Heng, Jeyoung Kim, Joonho Lee, Joonseok Lee, Xiaoxiao Li, Peng Liu, Shuai Lu, Balamurali Murugesan, Valery Naranjo, Sai Samarth R. Phaye, Sharath M. Shankaranarayana, Apoorva Sikka, Jaemin Son, Anton Van Den Hengel, Shujun Wang, Junyan Wu, Zifeng Wu, Guanghui Xu, Yongli Xu, Pengshuai Yin, Fei Li, Yanwu Xu, Xiulan Zhang, Hrvoje Bogunović
As part of REFUGE, we have publicly released a data set of 1200 fundus images with ground truth segmentations and clinical glaucoma labels, currently the largest existing one.
We propose an approach to semantic (image) segmentation that reduces the computational costs by a factor of 25 with limited impact on the quality of results.
As a result, we are able to derive a new, shallower, architecture of residual networks which significantly outperforms much deeper models such as ResNet-200 on the ImageNet classification dataset.
Ranked #17 on Semantic Segmentation on PASCAL VOC 2012 test
(iii) As the performance of semantic category segmentation has a significant impact on the instance-level segmentation, which is the second step of our approach, we train fully convolutional residual networks to achieve the best semantic category segmentation accuracy.
Ranked #38 on Semantic Segmentation on PASCAL Context
Then we train fully convolutional deep residual networks to predict the depth label of each pixel.
(i) First, we evaluate different variations of a fully convolutional residual network so as to find the best configuration, including the number of layers, the resolution of feature maps, and the size of field-of-view.