Warp-Refine Propagation: Semi-Supervised Auto-labeling via Cycle-consistency

TL;DR

This paper introduces Warp-Refine Propagation, a semi-supervised method that combines semantic and geometric cues with cycle consistency to auto-label videos, significantly improving semantic segmentation accuracy.

Contribution

It presents a novel label propagation technique that refines geometrically-warped labels with semantic priors using cycle consistency, advancing semi-supervised video annotation.

Findings

Improves label propagation by 13.1 mIoU on ApolloScape

Achieves state-of-the-art results on NYU-V2 and KITTI datasets

Matches best results on Cityscapes dataset

Abstract

Deep learning models for semantic segmentation rely on expensive, large-scale, manually annotated datasets. Labelling is a tedious process that can take hours per image. Automatically annotating video sequences by propagating sparsely labeled frames through time is a more scalable alternative. In this work, we propose a novel label propagation method, termed Warp-Refine Propagation, that combines semantic cues with geometric cues to efficiently auto-label videos. Our method learns to refine geometrically-warped labels and infuse them with learned semantic priors in a semi-supervised setting by leveraging cycle consistency across time. We quantitatively show that our method improves label-propagation by a noteworthy margin of 13.1 mIoU on the ApolloScape dataset. Furthermore, by training with the auto-labelled frames, we achieve competitive results on three semantic-segmentation benchmarks, improving the state-of-the-art by a large margin of 1.8 and 3.61 mIoU on NYU-V2 and KITTI, while matching the current best results on Cityscapes.