DeepAI AI Chat
Log In Sign Up

Interpretable Image Classification with Differentiable Prototypes Assignment

by   Dawid Rymarczyk, et al.

We introduce ProtoPool, an interpretable image classification model with a pool of prototypes shared by the classes. The training is more straightforward than in the existing methods because it does not require the pruning stage. It is obtained by introducing a fully differentiable assignment of prototypes to particular classes. Moreover, we introduce a novel focal similarity function to focus the model on the rare foreground features. We show that ProtoPool obtains state-of-the-art accuracy on the CUB-200-2011 and the Stanford Cars datasets, substantially reducing the number of prototypes. We provide a theoretical analysis of the method and a user study to show that our prototypes are more distinctive than those obtained with competitive methods.


page 1

page 2

page 4

page 6

page 8

page 12

page 14

page 15


ProtoPShare: Prototype Sharing for Interpretable Image Classification and Similarity Discovery

In this paper, we introduce ProtoPShare, a self-explained method that in...

Differentiable Channel Pruning Search

In this paper, we propose the differentiable channel pruning search (DCP...

Differentiable Approximation Bridges For Training Networks Containing Non-Differentiable Functions

Modern neural network training relies on piece-wise (sub-)differentiable...

FeTa: A DCA Pruning Algorithm with Generalization Error Guarantees

Recent DNN pruning algorithms have succeeded in reducing the number of p...

Learning relationships between data obtained independently

The aim of this paper is to provide a new method for learning the relati...

Interpretable Neuroevolutionary Models for Learning Non-Differentiable Functions and Programs

A key factor in the modern success of deep learning is the astonishing e...

Automatic discovery of discriminative parts as a quadratic assignment problem

Part-based image classification consists in representing categories by s...