Dynamic Label Injection for Imbalanced Industrial Defect Segmentation

TL;DR

This paper introduces Dynamic Label Injection, a novel method for addressing class imbalance in industrial defect segmentation by re-balancing input batches through defect transfer techniques, improving performance especially in weakly-supervised scenarios.

Contribution

It presents a new algorithm that dynamically balances class distribution in training batches for defect segmentation, enhancing accuracy over existing methods.

Findings

DLI outperforms other balancing loss approaches on Magnetic Tiles dataset.

Effective in weakly-supervised defect segmentation.

Improves training stability and segmentation accuracy.

Abstract

In this work, we propose a simple yet effective method to tackle the problem of imbalanced multi-class semantic segmentation in deep learning systems. One of the key properties for a good training set is the balancing among the classes. When the input distribution is heavily imbalanced in the number of instances, the learning process could be hindered or difficult to carry on. To this end, we propose a Dynamic Label Injection (DLI) algorithm to impose a uniform distribution in the input batch. Our algorithm computes the current batch defect distribution and re-balances it by transferring defects using a combination of Poisson-based seamless image cloning and cut-paste techniques. A thorough experimental section on the Magnetic Tiles dataset shows better results of DLI compared to other balancing loss approaches also in the challenging weakly-supervised setup. The code is available at https://github.com/covisionlab/dynamic-label-injection.git