Unlock instant, AI-driven research and patent intelligence for your innovation.

A Domain Adaptive Semantic Segmentation Approach to Enhanced Adversarial Learning in Feature Spaces

A feature space and domain adaptive technology, applied in neural learning methods, instruments, biological neural network models, etc., can solve problems such as distorted feature distribution, unbalanced confrontation training, and inability to predict the structured output of the target domain. Adaptive, Enhanced Feature Encoder Effects

Active Publication Date: 2022-02-15
南京码极客科技有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0012] Aiming at the problems in the existing feature space confrontational learning method, such as unbalanced confrontational training, easy distortion of the original feature distribution, and inability to predict the structured output of the target domain, the present invention proposes a domain adaptive method for enhancing feature space confrontational learning Semantic segmentation method, the present invention effectively alleviates the training imbalance and feature distortion problems in the feature space confrontational learning method and the classifier over-fit The problem of combined source domain features promotes the network to better extract domain-invariant features and enhances the network's generalization ability. Domain-adaptive semantic segmentation algorithm for enhanced feature space confrontation learning

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
  • A Domain Adaptive Semantic Segmentation Approach to Enhanced Adversarial Learning in Feature Spaces
  • A Domain Adaptive Semantic Segmentation Approach to Enhanced Adversarial Learning in Feature Spaces
  • A Domain Adaptive Semantic Segmentation Approach to Enhanced Adversarial Learning in Feature Spaces

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0078] This embodiment proposes a domain-adaptive semantic segmentation method that enhances feature space adversarial learning, such as figure 1 , figure 2 As shown, the domain-adaptive semantic segmentation system based on enhanced feature space adversarial learning includes the following steps:

[0079] Step 1: Use a feature encoder to perform feature extraction on source domain images and target domain images to generate source domain image features and target domain image features;

[0080] Step 2: Perform feature space adversarial learning on source domain image features and target domain image features using a classification constraint discriminator;

[0081] Step 3: Using a combination of confrontational learning and pseudo-label self-training, the source domain image features and the target domain image features are segmented through the shared classifier, and the source domain image feature segmentation map and the target domain image feature segmentation map are o...

Embodiment 2

[0091] In this embodiment, on the basis of the above-mentioned embodiment 1, in order to better realize the present invention, further, in the step 2, in the classification constraint discriminator, the classifier component is used as a constraint, and the source domain characteristic of the discriminator is given Structural information, forcing the feature encoder to extract domain-invariant features containing structural information from the target domain to confuse the discriminator; in the process, after inputting the source domain image features and target domain image features into the classification constraint discriminator, the classification constraint discriminator is used loss For training, the specific formula is as follows:

[0092] ;

[0093] In the formula, the first two items on the right side of the equal sign are the loss function of the discriminator, and the third item is the auxiliary segmentation loss for the source domain output of the classifier; C ...

Embodiment 3

[0099] In this embodiment, on the basis of any one of the above-mentioned embodiments 1-2, in order to better realize the present invention, further, in the step 3:

[0100] For source domain data marked with : using forecast and the ground-truth label Between the cross entropy loss function to train the segmentation network, the specific loss function is as follows:

[0101] ;

[0102] where G1 represents the segmentation network, h and w represent the height and width of the input image, C2 represents the predefined category, and c represents the category.

[0103] In order to better realize the present invention, further, in the step 3:

[0104] For unlabeled target domain image features: Generate pseudo-labels for target domain image features during self-training, and use pseudo-labels to guide network updates. The specific operations are:

[0105] First, from the entire target domain data through the pre-trained model Select pixels with high prediction confide...

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 present invention proposes a domain-adaptive semantic segmentation method that enhances feature space adversarial learning. By introducing a classification constraint discriminator and a hybrid collaborative framework that combines adversarial learning and pseudo-label self-training, it effectively alleviates the problem of feature space adversarial learning. The problem of training imbalance and feature distortion and the problem of classifier overfitting the source domain features promote the network to better extract domain invariant features and improve the network generalization ability of the enhanced feature space adversarial learning domain-adaptive semantic segmentation algorithm.

Description

technical field [0001] The invention belongs to an unsupervised domain adaptive semantic segmentation method, in particular to a domain adaptive semantic segmentation method that enhances feature space confrontation learning. Background technique [0002] The purpose of semantic segmentation is to predict the structured output of the input image by marking each pixel. As an important topic in the field of computer vision, semantic segmentation has important applications in the fields of autonomous driving and medical image analysis. The current semantic segmentation method is mainly based on the latest progress of deep convolutional neural network. With the emergence of fully convolutional networks (FCN), the semantic segmentation algorithm with FCN as the backbone network has achieved great success. However, training deep neural networks requires a large amount of annotated training data. Different from image classification tasks to predict labels of images, semantic segme...

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 Patents(China)
IPC IPC(8): G06V10/26G06V10/40G06V10/764G06V10/774G06V10/82G06K9/62G06N3/08
CPCG06N3/088G06F18/24G06F18/214
Inventor 陈涛姚亚洲孙泽人沈复民
Owner 南京码极客科技有限公司