Computer Vision
 
Edit

Image Retrieval

672 papers with code • 54 benchmarks • 75 datasets

Image Retrieval is a fundamental and long-standing computer vision task that involves finding images similar to a provided query from a large database. It's often considered as a form of fine-grained, instance-level classification. Not just integral to image recognition alongside classification and detection, it also holds substantial business value by helping users discover images aligning with their interests or requirements, guided by visual similarity or other parameters.

( Image credit: DELF )

Libraries

Use these libraries to find Image Retrieval models and implementations
huggingface/transformers
4 papers
126,353
OML-Team/open-metric-learning
4 papers
781
kornia/kornia
2 papers
9,474
salesforce/lavis
2 papers
8,890
See all 10 libraries.

Datasets

Subtasks

Most implemented papers

Most implemented Social Latest No code

Kornia: an Open Source Differentiable Computer Vision Library for PyTorch

kornia/kornia • • 5 Oct 2019

This work presents Kornia -- an open source computer vision library which consists of a set of differentiable routines and modules to solve generic computer vision problems.

4
Paper
Code

Unifying Deep Local and Global Features for Image Search

tensorflow/models • • ECCV 2020

Image retrieval is the problem of searching an image database for items that are similar to a query image.

4
Paper
Code

Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval

cvdfoundation/google-landmark • • 3 Apr 2020

GLDv2 is the largest such dataset to date by a large margin, including over 5M images and 200k distinct instance labels.

4
Paper
Code

Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks

microsoft/Oscar • • ECCV 2020

Large-scale pre-training methods of learning cross-modal representations on image-text pairs are becoming popular for vision-language tasks.

4
Paper
Code

SEMICON: A Learning-to-hash Solution for Large-scale Fine-grained Image Retrieval

njust-vipgroup/semicon • 28 Sep 2022

In this paper, we propose Suppression-Enhancing Mask based attention and Interactive Channel transformatiON (SEMICON) to learn binary hash codes for dealing with large-scale fine-grained image retrieval tasks.

4
Paper
Code

Deep Image Retrieval: Learning global representations for image search

tensorflow/models • • 5 Apr 2016

We propose a novel approach for instance-level image retrieval.

3
Paper
Code

Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representations

gtolias/mom • • CVPR 2017

The diffusion is carried out on descriptors of overlapping image regions rather than on a global image descriptor like in previous approaches.

3
Paper
Code

Repeatability Is Not Enough: Learning Affine Regions via Discriminability

ducha-aiki/affnet • • ECCV 2018

A method for learning local affine-covariant regions is presented.

3
Paper
Code

Single Shot Scene Text Retrieval

lluisgomez/single-shot-str • • ECCV 2018

In this way, the text based image retrieval task can be casted as a simple nearest neighbor search of the query text representation over the outputs of the CNN over the entire image database.

3
Paper
Code

Detect-to-Retrieve: Efficient Regional Aggregation for Image Search

tensorflow/models • • CVPR 2019

Then, we demonstrate how a trained landmark detector, using our new dataset, can be leveraged to index image regions and improve retrieval accuracy while being much more efficient than existing regional methods.

3
Paper
Code
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy