Class2Str: End to End Latent Hierarchy Learning

08/20/2018
by   Soham Saha, et al.
0

Deep neural networks for image classification typically consists of a convolutional feature extractor followed by a fully connected classifier network. The predicted and the ground truth labels are represented as one hot vectors. Such a representation assumes that all classes are equally dissimilar. However, classes have visual similarities and often form a hierarchy. Learning this latent hierarchy explicitly in the architecture could provide invaluable insights. We propose an alternate architecture to the classifier network called the Latent Hierarchy (LH) Classifier and an end to end learned Class2Str mapping which discovers a latent hierarchy of the classes. We show that for some of the best performing architectures on CIFAR and Imagenet datasets, the proposed replacement and training by LH classifier recovers the accuracy, with a fraction of the number of parameters in the classifier part. Compared to the previous work of HDCNN, which also learns a 2 level hierarchy, we are able to learn a hierarchy at an arbitrary number of levels as well as obtain an accuracy improvement on the Imagenet classification task over them. We also verify that many visually similar classes are grouped together, under the learnt hierarchy.

READ FULL TEXT
research
07/08/2017

Embedding Visual Hierarchy with Deep Networks for Large-Scale Visual Recognition

In this paper, a level-wise mixture model (LMM) is developed by embeddin...
research
05/19/2021

Correlated Input-Dependent Label Noise in Large-Scale Image Classification

Large scale image classification datasets often contain noisy labels. We...
research
11/17/2019

Learning with Hierarchical Complement Objective

Label hierarchies widely exist in many vision-related problems, ranging ...
research
09/10/2019

Towards Interpretable Image Synthesis by Learning Sparsely Connected AND-OR Networks

This paper proposes interpretable image synthesis by learning hierarchic...
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
10/17/2017

Do Convolutional Neural Networks Learn Class Hierarchy?

Convolutional Neural Networks (CNNs) currently achieve state-of-the-art ...
research
04/20/2016

Network of Experts for Large-Scale Image Categorization

We present a tree-structured network architecture for large scale image ...

Please sign up or login with your details

Forgot password? Click here to reset