Papers › DHOG: Deep Hierarchical Object Grouping

DHOG: Deep Hierarchical Object Grouping

13 Mar 2020arXiv:2003.08821archive 2025-07-28

Luke Nicholas Darlow, Amos Storkey

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% on CIFAR-10, 1.5% on CIFAR-100-20, and 7.2% on SVHN.

Paper PDF Conference PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Clustering Edge Detection Image Clustering Object Representation Learning

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Image Clustering	CIFAR-10	DHOG	ARI	0.492	#30 of 40	Archive leaderboard	report
Image Clustering	CIFAR-10	DHOG	Accuracy	0.666	#30 of 40	Archive leaderboard	report
Image Clustering	CIFAR-10	DHOG	Backbone	ResNet-18	#30 of 40	Archive leaderboard	report
Image Clustering	CIFAR-10	DHOG	NMI	0.585	#30 of 40	Archive leaderboard	report
Image Clustering	CIFAR-10	DHOG	Train set	Train+Test	#30 of 40	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections