In:
Journal of Physics: Conference Series, IOP Publishing, Vol. 1952, No. 2 ( 2021-06-01), p. 022019-
Abstract:
A novel loss function based on category distribution for semantic segmentation is proposed in this paper. The new loss function is composed of two parts: (1) Pixel-wise cross-entropy. (2) Category distribution loss proposed. Most of existing semantic segmentation networks adopt a single pixel-wise cross-entropy loss function, which guides the network to independently predict the class each pixel belongs to. The downside is that ignoring global information of the image -- the distribution of all kinds of objects in the image, resulting in an unsatisfactory segmentation result. Category distribution loss proposed in this paper obtins category distribution information of the whole image by calculating the percentage of pixels to each class of objets. Acquired category distribution information can be represented as a feature vector, the distance of two vectors between prediction and ground truth forms category distribution loss. The new loss function measures the difference between pixels as well as the difference between global information. We apply the new loss to several classical networks, its pixel accuracy and mIoU accuracy on two benchmark datasets CamVid and Pascal VOC2012 are improved compared to using only pixel-wise cross-entropy. In addition, we also introduced the attention mechanism, which proved to be able to improve segmentation accuracy of the networks as well.
Type of Medium:
Online Resource
ISSN:
1742-6588
,
1742-6596
DOI:
10.1088/1742-6596/1952/2/022019
Language:
Unknown
Publisher:
IOP Publishing
Publication Date:
2021
detail.hit.zdb_id:
2166409-2
Permalink