Learning Hierarchy Aware Features for Reducing Mistake Severity

07/26/2022
by   Ashima Garg, et al.
5

Label hierarchies are often available apriori as part of biological taxonomy or language datasets WordNet. Several works exploit these to learn hierarchy aware features in order to improve the classifier to make semantically meaningful mistakes while maintaining or reducing the overall error. In this paper, we propose a novel approach for learning Hierarchy Aware Features (HAF) that leverages classifiers at each level of the hierarchy that are constrained to generate predictions consistent with the label hierarchy. The classifiers are trained by minimizing a Jensen-Shannon Divergence with target soft labels obtained from the fine-grained classifiers. Additionally, we employ a simple geometric loss that constrains the feature space geometry to capture the semantic structure of the label space. HAF is a training time approach that improves the mistakes while maintaining top-1 error, thereby, addressing the problem of cross-entropy loss that treats all mistakes as equal. We evaluate HAF on three hierarchical datasets and achieve state-of-the-art results on the iNaturalist-19 and CIFAR-100 datasets. The source code is available at https://github.com/07Agarg/HAF

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/26/2023

Label-Aware Hyperbolic Embeddings for Fine-grained Emotion Classification

Fine-grained emotion classification (FEC) is a challenging task. Specifi...
research
10/19/2022

Hierarchical classification at multiple operating points

Many classification problems consider classes that form a hierarchy. Cla...
research
04/01/2021

No Cost Likelihood Manipulation at Test Time for Making Better Mistakes in Deep Networks

There has been increasing interest in building deep hierarchy-aware clas...
research
03/10/2023

Inducing Neural Collapse to a Fixed Hierarchy-Aware Frame for Reducing Mistake Severity

There is a recently discovered and intriguing phenomenon called Neural C...
research
06/21/2023

Lightweight learning from label proportions on satellite imagery

This work addresses the challenge of producing chip level predictions on...
research
04/26/2023

SEAL: Simultaneous Label Hierarchy Exploration And Learning

Label hierarchy is an important source of external knowledge that can en...
research
10/03/2022

Language-Aware Soft Prompting for Vision Language Foundation Models

This paper is on soft prompt learning for Vision & Language (V L) mode...

Please sign up or login with your details

Forgot password? Click here to reset