DCSNet: A Surface Defect Classification and Segmentation Model by One-Class Learning
نویسندگان
چکیده
Abstract Researches in surface defect classification and segmentation technology have been seen significant progress recent years. However, there are few works on One-Class learning this direction by a single model. In previous researches, some problems remain unsolved the detection methods, e.g. training needs large number of samples these models cannot classify locate accurately, etc. The main contribution work is that we summarize overall ideas research network design propose multi-task model which could be trained only using positive samples. Meanwhile, experiments AITEX datasets[1] get 84.4% DR, 4.4% FAR 34.2% MIOU, conduct an ablation experiment real industrial product dataset to validate effect different backbones DCSNet. It’s worth mentioning DCSNet provides solution task based learning. code will open source ext-link-type="uri" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="https://agit.ai/wyxxx/zhengtu">https://agit.ai/wyxxx/zhengtu.
منابع مشابه
One-Class Classification with Extreme Learning Machine
One-class classification problemhas been investigated thoroughly for past decades. Among one of themost effective neural network approaches for one-class classification, autoencoder has been successfully applied for many applications. However, this classifier relies on traditional learning algorithms such as backpropagation to train the network, which is quite time-consuming. To tackle the slow...
متن کاملLearning a Classification Model for Segmentation
We propose a two-class classification model for grouping. Human segmented natural images are used as positive examples. Negative examples of grouping are constructed by randomly matching human segmentations and images. In a preprocessing stage an image is oversegmented into superpixels. We define a variety of features derived from the classical Gestalt cues, including contour, texture, brightne...
متن کاملLearning Deep Features for One-Class Classification
We propose a deep learning-based solution for the problem of feature learning in one-class classification. The proposed method operates on top of a Convolutional Neural Network (CNN) of choice and produces descriptive features while maintaining a low intra-class variance in the feature space for the given class. For this purpose two loss functions, compactness loss and descriptiveness loss are ...
متن کاملVideo Segmentation by Event Detection: A Novel One-Class Classification Approach
Segmenting videos into meaningful image sequences of some particular activities is an interesting problem in computer vision. In this paper, a novel algorithm is presented to achieve this semantic video segmentation. The goal is to make the system work unsupervised and generic in terms of application scenarios. The segmentation task is accomplished through event detection in a frameby-frame pro...
متن کاملOne-Class Classification by Combining Density and Class Probability Estimation
One-class classification has important applications such as outlier and novelty detection. It is commonly tackled using either density estimation techniques or by adapting a standard classification algorithm to the problem of carving out a decision boundary that describes the location of the target data. In this paper we present a simple method for one-class classification that combines the app...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of physics
سال: 2021
ISSN: ['0022-3700', '1747-3721', '0368-3508', '1747-3713']
DOI: https://doi.org/10.1088/1742-6596/1914/1/012037