All you need are a few pixels: semantic segmentation with PixelPick

TL;DR

This paper demonstrates that high-quality semantic segmentation can be achieved with very few carefully selected pixel labels, significantly reducing annotation costs through an active learning approach called PixelPick.

Contribution

It introduces a novel setting with sparse pixel labels, an active learning framework PixelPick, and extensive experiments showing comparable performance with minimal annotations.

Findings

Achieves competitive segmentation with up to 100x fewer labels.

Effective pixel sampling improves annotation efficiency.

Robustness to annotator error demonstrated.

Abstract

A central challenge for the task of semantic segmentation is the prohibitive cost of obtaining dense pixel-level annotations to supervise model training. In this work, we show that in order to achieve a good level of segmentation performance, all you need are a few well-chosen pixel labels. We make the following contributions: (i) We investigate the novel semantic segmentation setting in which labels are supplied only at sparse pixel locations, and show that deep neural networks can use a handful of such labels to good effect; (ii) We demonstrate how to exploit this phenomena within an active learning framework, termed PixelPick, to radically reduce labelling cost, and propose an efficient "mouse-free" annotation strategy to implement our approach; (iii) We conduct extensive experiments to study the influence of annotation diversity under a fixed budget, model pretraining, model capacity and the sampling mechanism for picking pixels in this low annotation regime; (iv) We provide comparisons to the existing state of the art in semantic segmentation with active learning, and demonstrate comparable performance with up to two orders of magnitude fewer pixel annotations on the CamVid, Cityscapes and PASCAL VOC 2012 benchmarks; (v) Finally, we evaluate the efficiency of our annotation pipeline and its sensitivity to annotator error to demonstrate its practicality.