DHOG: Deep Hierarchical Object Grouping

03/13/2020
by   Luke Nicholas Darlow, et al.
0

Recently, a number of competitive methods have tackled unsupervised representation learning by maximising the mutual information between the representations produced from augmentations. The resulting representations are then invariant to stochastic augmentation strategies, and can be used for downstream tasks such as clustering or classification. Yet data augmentations preserve many properties of an image and so there is potential for a suboptimal choice of representation that relies on matching easy-to-find features in the data. We demonstrate that greedy or local methods of maximising mutual information (such as stochastic gradient optimisation) discover local optima of the mutual information criterion; the resulting representations are also less-ideally suited to complex downstream tasks. Earlier work has not specifically identified or addressed this issue. We introduce deep hierarchical object grouping (DHOG) that computes a number of distinct discrete representations of images in a hierarchical order, eventually generating representations that better optimise the mutual information objective. We also find that these representations align better with the downstream task of grouping into underlying object classes. We tested DHOG on unsupervised clustering, which is a natural downstream test as the target representation is a discrete labelling of the data. We achieved new state-of-the-art results on the three main benchmarks without any prefiltering or Sobel-edge detection that proved necessary for many previous methods to work. We obtain accuracy improvements of: 4.3

READ FULL TEXT

page 5

page 10

page 11

page 12

page 14

research
03/08/2021

Multimodal Representation Learning via Maximization of Local Mutual Information

We propose and demonstrate a representation learning approach by maximiz...
research
03/28/2019

Wasserstein Dependency Measure for Representation Learning

Mutual information maximization has emerged as a powerful learning objec...
research
06/04/2020

Info3D: Representation Learning on 3D Objects using Mutual Information Maximization and Contrastive Learning

A major endeavor of computer vision is to represent, understand and extr...
research
12/07/2021

Unsupervised Representation Learning via Neural Activation Coding

We present neural activation coding (NAC) as a novel approach for learni...
research
10/11/2022

Word Sense Induction with Hierarchical Clustering and Mutual Information Maximization

Word sense induction (WSI) is a difficult problem in natural language pr...
research
11/20/2022

Towards Generalizable Graph Contrastive Learning: An Information Theory Perspective

Graph contrastive learning (GCL) emerges as the most representative appr...
research
02/20/2020

Neural Bayes: A Generic Parameterization Method for Unsupervised Representation Learning

We introduce a parameterization method called Neural Bayes which allows ...

Please sign up or login with your details

Forgot password? Click here to reset