Automatic discovery of discriminative parts as a quadratic assignment problem

11/14/2016
by   Ronan Sicre, et al.
0

Part-based image classification consists in representing categories by small sets of discriminative parts upon which a representation of the images is built. This paper addresses the question of how to automatically learn such parts from a set of labeled training images. The training of parts is cast as a quadratic assignment problem in which optimal correspondences between image regions and parts are automatically learned. The paper analyses different assignment strategies and thoroughly evaluates them on two public datasets: Willow actions and MIT 67 scenes. State-of-the art results are obtained on these datasets.

READ FULL TEXT
research
09/14/2015

Expanded Parts Model for Semantic Description of Humans in Still Images

We introduce an Expanded Parts Model (EPM) for recognizing human attribu...
research
12/20/2014

Automatic Discovery and Optimization of Parts for Image Classification

Part-based representations have been shown to be very useful for image c...
research
08/19/2019

Deep Weisfeiler-Lehman Assignment Kernels via Multiple Kernel Learning

Kernels for structured data are commonly obtained by decomposing objects...
research
06/03/2016

On Valid Optimal Assignment Kernels and Applications to Graph Classification

The success of kernel methods has initiated the design of novel positive...
research
11/29/2020

ProtoPShare: Prototype Sharing for Interpretable Image Classification and Similarity Discovery

In this paper, we introduce ProtoPShare, a self-explained method that in...
research
06/30/2023

A Parts Based Registration Loss for Detecting Knee Joint Areas

In this paper, a parts based loss is considered for finetune registering...
research
03/14/2016

Visual Concept Recognition and Localization via Iterative Introspection

Convolutional neural networks have been shown to develop internal repres...

Please sign up or login with your details

Forgot password? Click here to reset