Modified Semi-Supervised Adversarial Deep Network and Classifier Combination for Segmentation of Satellite Images

Semi and Weakly Supervised Semantic Segmentation Using Generative Adversarial Network

Semantic segmentation has been a long standing challenging task in computer vision. It aims at assigning a label to each image pixel and needs significant number of pixellevel annotated data, which is often unavailable. To address this lack, in this paper, we leverage, on one hand, massive amount of available unlabeled or weakly labeled data, and on the other hand, non-real images created throu...

Adversarial Learning for Semi-Supervised Semantic Segmentation

We propose a method 1 for semi-supervised semantic segmentation using the adversarial network. While most existing discriminators are trained to classify input images as real or fake on the image level, we design a discriminator in a fully convolutional manner to differentiate the predicted probability maps from the ground truth segmentation distribution with the consideration of the spatial re...

Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation

We propose a novel deep neural network architecture for semi-supervised semantic segmentation using heterogeneous annotations. Contrary to existing approaches posing semantic segmentation as a single task of region-based classification, our algorithm decouples classification and segmentation, and learns a separate network for each task. In this architecture, labels associated with an image are ...

Semi-supervised segmentation of images

Segmentation of patterns in images is usually based on the processing chain ”segmentation – feature extraction – classification”. It will be described, how for an arbitrary application an automatic processing stream can be generated with an initial feed back from an expert. The core of this new method is an automatic generator of optimized classifications and an example based interactive featur...

Multi Resolution Fuzzy Segmentation of Satellite Images