Deeply Explain CNN Via Hierarchical Decomposition

Building Steady-State Simulators via Hierarchical Feedback Decomposition

In recent years, compositional modeling and selfexplanatory simulation techniques have simplified the process of building dynamic simulators of physical systems. Building steady-state simulators is, conceptually, a simpler task consisting in solving a set algebraic equations. This simplicity hides delicate technical issues of convergence and search-space size due to the potentially large number...

Hierarchical Learning for Large-Scale Image Classification via CNN and Maximum Confidence Path

Hierarchical Comprehensive Triangular Decomposition

The concept of comprehensive triangular decomposition (CTD) was first introduced by Chen et al. in their CASC’2007 paper and could be viewed as an analogue of comprehensive Gröbner systems for parametric polynomial systems. The first complete algorithm for computing CTD was also proposed in that paper and implemented in the RegularChains library in Maple. Following our previous work on generic ...

Polyp detection in Colonoscopy Videos Using Deeply-Learned Hierarchical Features

This paper summarizes the method of polyp detection in colonoscopy images and provides preliminary results to participate in ISBI 2015 Grand Challenge on Automatic Polyp Detection in Colonoscopy videos. The key aspect of the proposed method is to learn hierarchical features using convolutional neural network. The features are learned in different scales to provide scale-invariant features throu...

Interpreting CNN knowledge via an Explanatory Graph

This paper learns a graphical model, namely an explanatory graph, which reveals the knowledge hierarchy hidden inside a pre-trained CNN. Considering that each filter in a convlayer of a pre-trained CNN usually represents a mixture of object parts, we propose a simple yet efficient method to automatically disentangles different part patterns from each filter, and construct an explanatory graph. ...