Coarse-to-Fine Annotation Enrichment for Semantic Segmentation Learning

TL;DR

This paper introduces a novel annotation enrichment strategy that transforms coarse annotations into finer, high-quality labels for semantic segmentation, significantly improving performance while reducing annotation costs.

Contribution

The proposed method automatically enriches coarse annotations to high-quality labels, enabling effective training of segmentation models with less manual effort.

Findings

Significant performance improvement over coarse labels

Competitive with fully annotated dense labels

Outperforms other weakly-supervised methods

Abstract

Rich high-quality annotated data is critical for semantic segmentation learning, yet acquiring dense and pixel-wise ground-truth is both labor- and time-consuming. Coarse annotations (e.g., scribbles, coarse polygons) offer an economical alternative, with which training phase could hardly generate satisfactory performance unfortunately. In order to generate high-quality annotated data with a low time cost for accurate segmentation, in this paper, we propose a novel annotation enrichment strategy, which expands existing coarse annotations of training data to a finer scale. Extensive experiments on the Cityscapes and PASCAL VOC 2012 benchmarks have shown that the neural networks trained with the enriched annotations from our framework yield a significant improvement over that trained with the original coarse labels. It is highly competitive to the performance obtained by using human annotated dense annotations. The proposed method also outperforms among other state-of-the-art weakly-supervised segmentation methods.