Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Attention enhancement out-of-distribution image detection method based on classifier prediction uncertainty

An uncertainty, image detection technology, applied in the direction of instruments, neural learning methods, biological neural network models, etc., can solve the problems of large coverage of out-of-distribution data, unable to give reliable results, and not very good results, and achieve classification The results are reliable, the detection effect is improved, and the detection effect is good.

Active Publication Date: 2021-04-16
SUN YAT SEN UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Compared with unsupervised anomaly detection methods, the out-of-distribution data coverage in this task is too large to be considered as the same class
[0003] At present, deep learning has become an important means to solve problems, but the problem is that many models can only be successfully applied when the test data and training data are similar, and often cannot be given when encountering some samples that are far from the distribution of training data. reliable results, and may even give a very confident but erroneous prediction
This method is relatively simple and direct, but the effect is not very good compared to other methods

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Attention enhancement out-of-distribution image detection method based on classifier prediction uncertainty
  • Attention enhancement out-of-distribution image detection method based on classifier prediction uncertainty
  • Attention enhancement out-of-distribution image detection method based on classifier prediction uncertainty

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The accompanying drawings are for illustrative purposes only and cannot be construed as limiting the patent;

[0033] In order to better illustrate this embodiment, some parts in the drawings will be omitted, enlarged or reduced, and do not represent the size of the actual product;

[0034] For those skilled in the art, it is understandable that some well-known structures and descriptions thereof may be omitted in the drawings.

[0035] The technical solutions of the present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0036] Such as Figure 1-2 As shown, an attention-enhanced out-of-distribution image detection method based on classifier prediction uncertainty includes the following steps:

[0037] S1: Image reconstruction feature extraction and dimensionality reduction processing;

[0038] S2: Use the low-dimensional data obtained in S1 to perform multi-classification probability calculations, and extrac...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides an attention enhancement out-of-distribution image detection method based on classifier prediction uncertainty. The uncertainty of the classifier is considered, so that the classification result is more reliable, and the uncertainty is used for weighting the features, so that the classifier pays more attention to the area where the sample is beneficial to classification, and the influence caused by inherent noise of samples in distribution is ignored, so that the effectiveness of the softmax maximum classification probability value in an out-of-distribution sample detection task is greatly improved, and the discrimination of the softmax maximum classification probability value in two types of data is greatly improved. For the out-of-distribution samples, a feature attention graph calculated by utilizing uncertainty can enable a classifier to pay attention to a more wrong region, so that a lower confidence score is caused, and the detection effect is further improved; the method is not excessively limited to training data, misjudgment is not likely to happen to edge samples, and a better detection effect can be obtained.

Description

technical field [0001] The invention relates to the field of out-of-distribution sample detection, and more specifically, to an attention-enhanced out-of-distribution image detection method based on classifier prediction uncertainty. Background technique [0002] Out-of-distribution images are data distributed far from the data used for training, often significantly different from in-distribution data. The method of detecting out-of-distribution data from a large number of in-distribution data is called out-of-distribution sample detection or outlier detection method. In contrast to anomaly detection tasks, out-of-distribution detection is usually applied to labeled data, i.e., considers identifiable categorical features of in-distribution samples of a dataset. Compared with unsupervised anomaly detection methods, the out-of-distribution data coverage in this task is too large to be considered as the same class. [0003] At present, deep learning has become an important me...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62G06N3/08
CPCY04S10/50
Inventor 苏勤亮高月
Owner SUN YAT SEN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products