Budget-aware Semi-Supervised Semantic and Instance Segmentation

TL;DR

This paper introduces a budget-aware semi-supervised segmentation method that significantly reduces annotation costs while outperforming weakly-supervised approaches, demonstrating effectiveness on Pascal VOC.

Contribution

It revisits semi-supervised segmentation, showing that with minimal annotation budgets, simple methods outperform weakly-supervised ones and outperform previous semi-supervised approaches at lower costs.

Findings

Semi-supervised methods outperform weakly-supervised ones at low annotation budgets.

The proposed approach outperforms previous semi-supervised methods with less labeling effort.

Results are demonstrated on the Pascal VOC benchmark.

Abstract

Methods that move towards less supervised scenarios are key for image segmentation, as dense labels demand significant human intervention. Generally, the annotation burden is mitigated by labeling datasets with weaker forms of supervision, e.g. image-level labels or bounding boxes. Another option are semi-supervised settings, that commonly leverage a few strong annotations and a huge number of unlabeled/weakly-labeled data. In this paper, we revisit semi-supervised segmentation schemes and narrow down significantly the annotation budget (in terms of total labeling time of the training set) compared to previous approaches. With a very simple pipeline, we demonstrate that at low annotation budgets, semi-supervised methods outperform by a wide margin weakly-supervised ones for both semantic and instance segmentation. Our approach also outperforms previous semi-supervised works at a much reduced labeling cost. We present results for the Pascal VOC benchmark and unify weakly and semi-supervised approaches by considering the total annotation budget, thus allowing a fairer comparison between methods.