Intersection Regularization for Extracting Semantic Attributes

by   Ameen Ali, et al.

We consider the problem of supervised classification, such that the features that the network extracts match an unseen set of semantic attributes, without any additional supervision. For example, when learning to classify images of birds into species, we would like to observe the emergence of features that zoologists use to classify birds. We propose training a neural network with discrete top-level activations, which is followed by a multi-layered perceptron (MLP) and a parallel decision tree. We present a theoretical analysis as well as a practical method for learning in the intersection of two hypothesis classes. Since real-world features are often sparse, a randomized sparsity regularization is also applied. Our results on multiple benchmarks show an improved ability to extract a set of features that are highly correlated with the set of unseen attributes.



There are no comments yet.


page 7


Only sparsity based loss function for learning representations

We study the emergence of sparse representations in neural networks. We ...

Isometric Propagation Network for Generalized Zero-shot Learning

Zero-shot learning (ZSL) aims to classify images of an unseen class only...

Correlated Feature Selection for Tweet Spam Classification using Artificial Neural Networks

Identification of spam messages is a very challenging task for social ne...

Moving Towards Open Set Incremental Learning: Readily Discovering New Authors

The classification of textual data often yields important information. M...

Automatic Attribute Discovery with Neural Activations

How can a machine learn to recognize visual attributes emerging out of o...

How to Transfer? Zero-Shot Object Recognition via Hierarchical Transfer of Semantic Attributes

Attribute based knowledge transfer has proven very successful in visual ...

Potential Features of ICU Admission in X-ray Images of COVID-19 Patients

X-ray images may present non-trivial features with predictive informatio...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.