Gating feature attention equivariant segmentation method based on weak supervised learning

Abstract

The invention discloses a gating feature attention isovariant segmentation method based on weak supervised learning, and the method specifically comprises the steps: 1, training a first classification network, and carrying out the weight sharing, and obtaining a second classification network; training a partial fusion module of the first gating, and carrying out weight sharing to obtain a partial fusion module of the second gating; 2, performing affine transformation on the original image to obtain an affine image; 3, respectively inputting the original image and the affine image into two classification networks; 4, taking the feature layer of the last layer of the two classification networks as class activation mapping and affine class activation mapping; 5, inputting the feature maps output by the two classification networks at the specific stage into a corresponding gated partial fusion module to obtain a gated feature map and an affine gated feature map; 6, inputting results obtained in the step 4 and the step 5 into a cross feature attention model to obtain improved class activation mapping; and 7, realizing image segmentation according to the improved class activation mapping. According to the invention, the segmentation precision of the weak supervision network is improved.

Description

technical field [0001] The invention belongs to the technical field of image processing. Background technique [0002] With the wide application of deep learning, computer vision technology has developed rapidly. Computer vision is a science that studies how to let machines replace human eyes to identify, track and detect real objects. It is a simulation of biological vision, where the computer replaces the human brain to analyze and process the image data, and ultimately hopes that the computer can observe and understand the world through "vision" like humans. [0003] Semantic segmentation is one of the main tasks of computer vision and a prerequisite for a large number of advanced vision tasks. The semantic segmentation network at this stage is divided into two categories: one is a strongly supervised segmentation network, which requires pixel-level annotation for objects in the segmented scene, and the production cost of the dataset is relatively high; the other is a w...

AI Technical Summary

Problems solved by technology

However, this global attention mechanism is aimed at all pixels in the image, and also requires corresponding pixel-level annotations for supervision, which cannot be achieved in weakly supervised segmentation networks.

Images