Scene Classification via a Gradient Boosting Random Convolutional Network Framework
IEEE Transactions on Geoscience and Remote Sensing, IF:3.36
Target: Can we find a way to combine different deep neural networks effectively and efficiently for scene classification, which can effectively combine many deep neural net works.
An ensemble of a number of neural networks can significantly improve the generalization ability of a neural network system. Different ways of combining neural networks:
- Simple averaging or weighted averaging
- Plurality voting or majority voting
- Adaptive boosting
- Gradient Boosting Machine : shown considerable promise in a wide range of practical applications
Image Segmentation using SLIC SuperPixels and DBSCAN Clustering
This segmentation approach makes use of Achanta et al’s SLIC superpixels and the DBSCAN clustering algorithm. The approach is simple and relatively fast.
- Application of the SLIC superpixel algorithm forms an over-segmentation of an image.
- These superpixels are then processed using the DBSCAN algorithm to form clusters of superpixels to generate the final segmentation.