Log In Sign Up

Evaluating Contrastive Models for Instance-based Image Retrieval

by   Tarun Krishna, et al.

In this work, we evaluate contrastive models for the task of image retrieval. We hypothesise that models that are learned to encode semantic similarity among instances via discriminative learning should perform well on the task of image retrieval, where relevancy is defined in terms of instances of the same object. Through our extensive evaluation, we find that representations from models trained using contrastive methods perform on-par with (and outperforms) a pre-trained supervised baseline trained on the ImageNet labels in retrieval tasks under various configurations. This is remarkable given that the contrastive models require no explicit supervision. Thus, we conclude that these models can be used to bootstrap base models to build more robust image retrieval engines.


page 1

page 2

page 3

page 4


Homography augumented momentum constrastive learning for SAR image retrieval

Deep learning-based image retrieval has been emphasized in computer visi...

Self-Supervised Consistent Quantization for Fully Unsupervised Image Retrieval

Unsupervised image retrieval aims to learn an efficient retrieval system...

Learning Deep Representations via Contrastive Learning for Instance Retrieval

Instance-level Image Retrieval (IIR), or simply Instance Retrieval, deal...

Vision Transformer Hashing for Image Retrieval

Deep learning has shown a tremendous growth in hashing techniques for im...

Indicative Image Retrieval: Turning Blackbox Learning into Grey

Deep learning became the game changer for image retrieval soon after it ...

MultiGrain: a unified image embedding for classes and instances

MultiGrain is a network architecture producing compact vector representa...

Cooperative Embeddings for Instance, Attribute and Category Retrieval

The goal of this paper is to retrieve an image based on instance, attrib...