DefectNET: multi-class fault detection on highly-imbalanced datasets

04/01/2019
by   N. Anantrasirichai, et al.
0

As a data-driven method, the performance of deep convolutional neural networks (CNN) relies heavily on training data. The prediction results of traditional networks give a bias toward larger classes, which tend to be the background in the semantic segmentation task. This becomes a major problem for fault detection, where the targets appear very small on the images and vary in both types and sizes. In this paper we propose a new network architecture, DefectNet, that offers multi-class (including but not limited to) defect detection on highly-imbalanced datasets. DefectNet consists of two parallel paths, which are a fully convolutional network and a dilated convolutional network to detect large and small objects respectively. We propose a hybrid loss maximising the usefulness of a dice loss and a cross entropy loss, and we also employ the leaky rectified linear unit (ReLU) to deal with rare occurrence of some targets in training batches. The prediction results show that our DefectNet outperforms state-of-the-art networks for detecting multi-class defects with the average accuracy improvement of approximately 10 turbine.

READ FULL TEXT

page 1

page 3

page 4

research
12/22/2014

Fully Convolutional Multi-Class Multiple Instance Learning

Multiple instance learning (MIL) can reduce the need for costly annotati...
research
07/03/2017

Generalised Wasserstein Dice Score for Imbalanced Multi-class Segmentation using Holistic Convolutional Networks

The Dice score is widely used for binary segmentation due to its robustn...
research
10/27/2022

Deep Convolutional Neural Networks for Multi-Target Tracking: A Transfer Learning Approach

Multi-target tracking (MTT) is a traditional signal processing task, whe...
research
01/30/2017

Fully Convolutional Architectures for Multi-Class Segmentation in Chest Radiographs

The success of deep convolutional neural networks on image classificatio...
research
09/14/2021

Predicting Loss Risks for B2B Tendering Processes

Sellers and executives who maintain a bidding pipeline of sales engageme...
research
02/02/2020

Towards Deep Machine Reasoning: a Prototype-based Deep Neural Network with Decision Tree Inference

In this paper we introduce the DMR – a prototype-based method and networ...
research
03/29/2017

Automatic Detection of Knee Joints and Quantification of Knee Osteoarthritis Severity using Convolutional Neural Networks

This paper introduces a new approach to automatically quantify the sever...

Please sign up or login with your details

Forgot password? Click here to reset