Paper summary 3

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.

  1. Application of the SLIC superpixel algorithm forms an over-segmentation of an image.
  2. These superpixels are then processed using the DBSCAN algorithm to form clusters of superpixels to generate the final segmentation.



Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s