Search Results for author:
Found 2 papers, 0 papers with code
Training Constrained Deconvolutional Networks for Road Scene Semantic Segmentation
In this work we investigate the problem of road scene semantic segmentation using Deconvolutional Networks (DNs).
A Unified Generative Adversarial Network Training via Self-Labeling and Self-Attention
However, because the classifier might still make mistakes, especially at the beginning of the training, we also refine the labels through self-attention, by using the labeling of real data samples only when the classifier outputs a high classification probability score.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
