2020
DOI: 10.48550/arxiv.2012.08466
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Objective-Based Hierarchical Clustering of Deep Embedding Vectors

Abstract: We initiate a comprehensive experimental study of objective-based hierarchical clustering methods on massive datasets consisting of deep embedding vectors from computer vision and NLP applications. This includes a large variety of image embedding (ImageNet, ImageNetV2, NaBirds), word embedding (Twitter, Wikipedia), and sentence embedding (SST-2) vectors from several popular recent models (e.g. ResNet, ResNext, Inception V3, SBERT). Our study includes datasets with up to 4.5 million entries with embedding dimen… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2021
2021
2021
2021

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(1 citation statement)
references
References 32 publications
0
1
0
Order By: Relevance
“…Hierarchical clustering has been applied in a wide variety of settings such as scientific discovery [1], personalization [2], entity resolution for knowledge-bases [3,4,5], and jet physics [6,7,8,9]. While much work has focused on approximation methods for relatively large datasets [10,11,12,13,14,15,16,17,18,19,20], there are also important use cases of hierarchical clustering that demand exact or high-quality approximations [21]. This .…”
Section: Introductionmentioning
confidence: 99%
“…Hierarchical clustering has been applied in a wide variety of settings such as scientific discovery [1], personalization [2], entity resolution for knowledge-bases [3,4,5], and jet physics [6,7,8,9]. While much work has focused on approximation methods for relatively large datasets [10,11,12,13,14,15,16,17,18,19,20], there are also important use cases of hierarchical clustering that demand exact or high-quality approximations [21]. This .…”
Section: Introductionmentioning
confidence: 99%