The scarcity of fully-annotated data becomes the biggest obstacle that prevents many deep learning approaches from widely applied. Weakly-supervised visual which can utilize inexact annotations is developed rapidly to remedy such a situation. In this paper, we study weakly-supervised task achieving pixel-level semantic segmentation only with image-level labels as supervision. Different other me...

With the development of artificial intelligence, more and people hope that computers can understand human language through natural technology, learn to think like beings, finally replace beings complete highly difficult tasks with cognitive ability. As key technology understanding, sentence representation reasoning mainly focuses on method model. Although performance has been improved, there ar...

The deep CNNs in image semantic segmentation typically require a large number of densely-annotated images for training and have difficulties generalizing to unseen object categories. Therefore, few-shot has been developed perform with just few annotated examples. In this work, we tackle the using self-regularized prototypical network (SRPNet) based on prototype extraction better utilization sup...

The current image semantic segmentation methods cannot meet the requirements of high precision and speed for remote sensing analysis. ENet network model builds a network, which has characteristics few parameters fast operation speed. attention mechanism module is integrated with model, can deeply mine features in datasets ensure accuracy segmentation. author combines to construct new model. fir...

Exemplar-based colorization approaches rely on reference image to provide plausible colors for target gray-scale image. The key and difficulty of exemplar-based is establish an accurate correspondence between these two images. Previous have attempted construct such a but are faced with obstacles. First, using luminance channel the calculation inaccurate. Second, dense they built introduces wron...