SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.13432 · ICCV · 2021

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

Rares, Ambrus, Adrien Gaidon, Shin-Ichi Maeda, Aditya Ganeshan, Yasunori Kudo, Dennis Park, Alexis Vallet, Tommi Kerola

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. We have no repository linked to it either. That is a statement about our graph, not about the paper.

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 semisupervised 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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2109.13432")
get_code_for_paper("2109.13432")
have("2109.13432")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2109.13432.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2109.13432.svg)](https://syntology.ai/paper/2109.13432)

Connect an agent — have() is free.