UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

MultiGrain: a unified image embedding for classes and instances

Berman, M; Jégou, H; Vedaldi, A; Kokkinos, I; Douze, M; (2019) MultiGrain: a unified image embedding for classes and instances. ArXiv: Ithaca, NY, USA. Green open access

[thumbnail of Multigrain.pdf]
Preview
Text
Multigrain.pdf - Accepted Version

Download (1MB) | Preview

Abstract

MultiGrain is a network architecture producing compact vector representations that are suited both for image classification and particular object retrieval. It builds on a standard classification trunk. The top of the network produces an embedding containing coarse and fine-grained information, so that images can be recognized based on the object class, particular object, or if they are distorted copies. Our joint training is simple: we minimize a cross-entropy loss for classification and a ranking loss that determines if two images are identical up to data augmentation, with no need for additional labels. A key component of MultiGrain is a pooling layer that takes advantage of high-resolution images with a network trained at a lower resolution. When fed to a linear classifier, the learned embeddings provide state-of-the-art classification accuracy. For instance, we obtain 79.4% top-1 accuracy with a ResNet-50 learned on Imagenet, which is a +1.8% absolute improvement over the AutoAugment method. When compared with the cosine similarity, the same embeddings perform on par with the state-of-the-art for image retrieval at moderate resolutions.

Type: Working / discussion paper
Title: MultiGrain: a unified image embedding for classes and instances
Open access status: An open access version is available from UCL Discovery
Publisher version: https://arxiv.org/abs/1902.05509
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10088673
Downloads since deposit
11Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item