Convolution-based Probability Gradient Loss for Semantic Segmentation

arXiv:2404.06704v1 Announce Type: new
Abstract: In this paper, we introduce a novel Convolution-based Probability Gradient (CPG) loss for semantic segmentation. It employs convolution kernels similar to the Sobel operator, capable of computing the gradient of pixel intensity in an image. This enables the computation of gradients for both ground-truth and predicted category-wise probabilities. It enhances network performance by maximizing the similarity between these two probability gradients. Moreover, to specifically enhance accuracy near the object's boundary, we extract the object boundary …

abstract arxiv computation computing convolution cpg cs.ai cs.cv gradient ground-truth image intensity loss novel paper pixel probability segmentation semantic truth type wise