Intersection Regularization for Extracting Semantic Attributes

03/22/2021
by   Ameen Ali, et al.
20

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.

READ FULL TEXT
research
07/19/2022

Few-shot Open-set Recognition Using Background as Unknowns

Few-shot open-set recognition aims to classify both seen and novel image...
research
03/07/2019

Only sparsity based loss function for learning representations

We study the emergence of sparse representations in neural networks. We ...
research
02/03/2021

Isometric Propagation Network for Generalized Zero-shot Learning

Zero-shot learning (ZSL) aims to classify images of an unseen class only...
research
11/06/2019

Correlated Feature Selection for Tweet Spam Classification using Artificial Neural Networks

Identification of spam messages is a very challenging task for social ne...
research
08/07/2023

Learning Concise and Descriptive Attributes for Visual Recognition

Recent advances in foundation models present new opportunities for inter...
research
03/05/2019

Multiple-Kernel Dictionary Learning for Reconstruction and Clustering of Unseen Multivariate Time-series

There exist many approaches for description and recognition of unseen cl...
research
04/05/2020

Long-tail learning with attributes

Learning to classify images with unbalanced class distributions is chall...

Please sign up or login with your details

Forgot password? Click here to reset