Parity Partition Coding for Sharp Multi-Label Classification

08/23/2019
by   Christopher G. Blake, et al.
0

The problem of efficiently training and evaluating image classifiers that can distinguish between a large number of object categories is considered. A novel metric, sharpness, is proposed which is defined as the fraction of object categories that are above a threshold accuracy. To estimate sharpness (along with a confidence value), a technique called fraction-accurate estimation is introduced which samples categories and samples instances from these categories. In addition, a technique called parity partition coding, a special type of error correcting output code, is introduced, increasing sharpness, while reducing the multi-class problem to a multi-label one with exponentially fewer outputs. We demonstrate that this approach outperforms the baseline model for both MultiMNIST and CelebA, while requiring fewer parameters and exceeding state of the art accuracy on individual labels.

READ FULL TEXT
research
09/03/2016

An Online Universal Classifier for Binary, Multi-class and Multi-label Classification

Classification involves the learning of the mapping function that associ...
research
06/27/2012

Maximum Margin Output Coding

In this paper we study output coding for multi-label prediction. For a m...
research
05/26/2020

Minimizing Supervision in Multi-label Categorization

Multiple categories of objects are present in most images. Treating this...
research
07/20/2020

Multi-label Contrastive Predictive Coding

Variational mutual information (MI) estimators are widely used in unsupe...
research
11/25/2021

ACPL: Anti-curriculum Pseudo-labelling forSemi-supervised Medical Image Classification

Effective semi-supervised learning (SSL) in medical im-age analysis (MIA...
research
04/22/2015

Exploit Bounding Box Annotations for Multi-label Object Recognition

Convolutional neural networks (CNNs) have shown great performance as gen...

Please sign up or login with your details

Forgot password? Click here to reset