Making CNNs Interpretable by Building Dynamic Sequential Decision Forests with Top-down Hierarchy Learning

06/05/2021
by   Yilin Wang, et al.
0

In this paper, we propose a generic model transfer scheme to make Convlutional Neural Networks (CNNs) interpretable, while maintaining their high classification accuracy. We achieve this by building a differentiable decision forest on top of CNNs, which enjoys two characteristics: 1) During training, the tree hierarchies of the forest are learned in a top-down manner under the guidance from the category semantics embedded in the pre-trained CNN weights; 2) During inference, a single decision tree is dynamically selected from the forest for each input sample, enabling the transferred model to make sequential decisions corresponding to the attributes shared by semantically-similar categories, rather than directly performing flat classification. We name the transferred model deep Dynamic Sequential Decision Forest (dDSDF). Experimental results show that dDSDF not only achieves higher classification accuracy than its conuterpart, i.e., the original CNN, but has much better interpretability, as qualitatively it has plausible hierarchies and quantitatively it leads to more precise saliency maps.

READ FULL TEXT

page 10

page 12

research
03/07/2022

Deep Neural Decision Forest for Acoustic Scene Classification

Acoustic scene classification (ASC) aims to classify an audio clip based...
research
07/08/2015

Feature Representation in Convolutional Neural Networks

Convolutional Neural Networks (CNNs) are powerful models that achieve im...
research
02/01/2018

Interpreting CNNs via Decision Trees

This paper presents a method to learn a decision tree to quantitatively ...
research
04/19/2019

Visualizing the decision-making process in deep neural decision forest

Deep neural decision forest (NDF) achieved remarkable performance on var...
research
10/27/2020

A short note on the decision tree based neural turing machine

Turing machine and decision tree have developed independently for a long...
research
10/02/2020

Attention augmented differentiable forest for tabular data

Differentiable forest is an ensemble of decision trees with full differe...

Please sign up or login with your details

Forgot password? Click here to reset