Improving Semantic Segmentation via Video Propagation and Label Relaxation

Semantic segmentation requires large amounts of pixel-wise annotations to learn accurate models. In this paper, we present a video prediction-based methodology to scale up training sets by synthesizing new training samples in order to improve the accuracy of semantic segmentation networks. We exploit video prediction models' ability to predict future frames in order to also predict future labels. A joint propagation strategy is also proposed to alleviate mis-alignments in synthesized samples. We demonstrate that training segmentation models on datasets augmented by the synthesized samples leads to significant improvements in accuracy. Furthermore, we introduce a novel boundary label relaxation technique that makes training robust to annotation noise and propagation artifacts along object boundaries. Our proposed methods achieve state-of-the-art mIoUs of 83.5% on Cityscapes and 82.9% on CamVid. Our single model, without model ensembles, achieves 72.8% mIoU on the KITTI semantic segmentation test set, which surpasses the winning entry of the ROB challenge 2018. Our code and videos can be found at

PDF Abstract CVPR 2019 PDF CVPR 2019 Abstract

Results from the Paper

 Ranked #1 on Semantic Segmentation on KITTI Semantic Segmentation (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Semantic Segmentation CamVid DeepLabV3Plus + SDCNetAug Mean IoU 81.7% # 3
Semantic Segmentation KITTI Semantic Segmentation DeepLabV3Plus + SDCNetAug Mean IoU (class) 72.83 # 1
class iIoU 48.68 # 1
Category IoU 88.99 # 1
Category iIoU 75.26 # 1


No methods listed for this paper. Add relevant methods here