An evaluation of large-scale methods for image instance and class discovery

08/09/2017
by   Matthijs Douze, et al.
0

This paper aims at discovering meaningful subsets of related images from large image collections without annotations. We search groups of images related at different levels of semantic, i.e., either instances or visual classes. While k-means is usually considered as the gold standard for this task, we evaluate and show the interest of diffusion methods that have been neglected by the state of the art, such as the Markov Clustering algorithm. We report results on the ImageNet and the Paris500k instance dataset, both enlarged with images from YFCC100M. We evaluate our methods with a labelling cost that reflects how much effort a human would require to correct the generated clusters. Our analysis highlights several properties. First, when powered with an efficient GPU implementation, the cost of the discovery process is small compared to computing the image descriptors, even for collections as large as 100 million images. Second, we show that descriptions selected for instance search improve the discovery of object classes. Third, the Markov Clustering technique consistently outperforms other methods; to our knowledge it has never been considered in this large scale scenario.

READ FULL TEXT

page 8

page 9

research
04/21/2016

LOH and behold: Web-scale visual search, recommendation and clustering using Locally Optimized Hashing

We propose a novel hashing-based matching scheme, called Locally Optimiz...
research
06/12/2021

Large-Scale Unsupervised Object Discovery

Existing approaches to unsupervised object discovery (UOD) do not scale ...
research
08/06/2020

Webly Supervised Semantic Embeddings for Large Scale Zero-Shot Learning

Zero-shot learning (ZSL) makes object recognition in images possible in ...
research
09/14/2017

Unsupervised deep object discovery for instance recognition

Severe background clutter is challenging in many computer vision tasks, ...
research
07/06/2020

Toward unsupervised, multi-object discovery in large-scale image collections

This paper addresses the problem of discovering the objects present in a...
research
08/26/2019

Learning to Discover Novel Visual Categories via Deep Transfer Clustering

We consider the problem of discovering novel object categories in an ima...
research
05/25/2018

Dynamicity and Durability in Scalable Visual Instance Search

Visual instance search involves retrieving from a collection of images t...

Please sign up or login with your details

Forgot password? Click here to reset