Investigating Shift Equivalence of Convolutional Neural Networks in Industrial Defect Segmentation

TL;DR

This paper introduces CAPS, a novel sampling method with adaptive boundary filtering and feature fusion, significantly improving shift equivalence and segmentation accuracy in industrial defect detection tasks.

Contribution

The paper proposes CAPS, a new down/upsampling technique with adaptive boundary filtering and feature fusion, enhancing shift equivalence and segmentation in CNNs for industrial defect segmentation.

Findings

CAPS improves shift equivalence over traditional methods.

The proposed method enhances segmentation accuracy on multiple datasets.

Experimental results show superior performance of CAPS in industrial defect segmentation.

Abstract

In industrial defect segmentation tasks, while pixel accuracy and Intersection over Union (IoU) are commonly employed metrics to assess segmentation performance, the output consistency (also referred to equivalence) of the model is often overlooked. Even a small shift in the input image can yield significant fluctuations in the segmentation results. Existing methodologies primarily focus on data augmentation or anti-aliasing to enhance the network's robustness against translational transformations, but their shift equivalence performs poorly on the test set or is susceptible to nonlinear activation functions. Additionally, the variations in boundaries resulting from the translation of input images are consistently disregarded, thus imposing further limitations on the shift equivalence. In response to this particular challenge, a novel pair of down/upsampling layers called component attention polyphase sampling (CAPS) is proposed as a replacement for the conventional sampling layers in CNNs. To mitigate the effect of image boundary variations on the equivalence, an adaptive windowing module is designed in CAPS to adaptively filter out the border pixels of the image. Furthermore, a component attention module is proposed to fuse all downsampled features to improve the segmentation performance. The experimental results on the micro surface defect (MSD) dataset and four real-world industrial defect datasets demonstrate that the proposed method exhibits higher equivalence and segmentation performance compared to other state-of-the-art methods.Our code will be available at https://github.com/xiaozhen228/CAPS.