A Weakly-Supervised Semantic Segmentation Approach based on the Centroid Loss: Application to Quality Control and Inspection

TL;DR

This paper introduces a novel weakly-supervised semantic segmentation method using a Centroid Loss to improve training with less detailed annotations, demonstrating competitive results in industrial quality control and defect inspection tasks.

Contribution

The paper proposes a new loss function incorporating Centroid Loss to enhance weakly-supervised segmentation, validated on industry-related datasets.

Findings

Achieved competitive segmentation performance with weak annotations.

Effective in industrial quality control and defect detection.

Centroid Loss improves pixel clustering during training.

Abstract

It is generally accepted that one of the critical parts of current vision algorithms based on deep learning and convolutional neural networks is the annotation of a sufficient number of images to achieve competitive performance. This is particularly difficult for semantic segmentation tasks since the annotation must be ideally generated at the pixel level. Weakly-supervised semantic segmentation aims at reducing this cost by employing simpler annotations that, hence, are easier, cheaper and quicker to produce. In this paper, we propose and assess a new weakly-supervised semantic segmentation approach making use of a novel loss function whose goal is to counteract the effects of weak annotations. To this end, this loss function comprises several terms based on partial cross-entropy losses, being one of them the Centroid Loss. This term induces a clustering of the image pixels in the object classes under consideration, whose aim is to improve the training of the segmentation network by guiding the optimization. The performance of the approach is evaluated against datasets from two different industry-related case studies: while one involves the detection of instances of a number of different object classes in the context of a quality control application, the other stems from the visual inspection domain and deals with the localization of images areas whose pixels correspond to scene surface points affected by a specific sort of defect. The detection results that are reported for both cases show that, despite the differences among them and the particular challenges, the use of weak annotations do not prevent from achieving a competitive performance level for both.