Computer Vision
 
Edit

Image Retrieval

665 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
5 papers
124,527
OML-Team/open-metric-learning
4 papers
757
kornia/kornia
2 papers
9,356
salesforce/lavis
2 papers
8,674
See all 10 libraries.

Datasets

Subtasks

Most implemented papers

Most implemented Social Latest No code

Learning Deep Representations of Fine-grained Visual Descriptions

hanzhanggit/StackGAN-v2 • • CVPR 2016

State-of-the-art methods for zero-shot visual recognition formulate learning as a joint embedding problem of images and side information.

9
Paper
Code

Looking at Outfit to Parse Clothing

kyamagu/js-segment-annotator • 4 Mar 2017

This paper extends fully-convolutional neural networks (FCN) for the clothing parsing problem.

9
Paper
Code

Combination of Multiple Global Descriptors for Image Retrieval

naver/cgd • • arXiv 2019

Recent studies in image retrieval task have shown that ensembling different models and combining multiple global descriptors lead to performance improvement.

7
Paper
Code

Particular object retrieval with integral max-pooling of CNN activations

naver/deep-image-retrieval • • 18 Nov 2015

Recently, image representation built upon Convolutional Neural Network (CNN) has been shown to provide effective descriptors for image search, outperforming pre-CNN features as short-vector representations.

6
Paper
Code

Stacked Cross Attention for Image-Text Matching

kuanghuei/SCAN • • ECCV 2018

Prior work either simply aggregates the similarity of all possible pairs of regions and words without attending differentially to more and less important words or regions, or uses a multi-step attentional process to capture limited number of semantic alignments which is less interpretable.

6
Paper
Code

CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples

filipradenovic/cnnimageretrieval-pytorch • • 8 Apr 2016

Convolutional Neural Networks (CNNs) achieve state-of-the-art performance in many computer vision tasks.

5
Paper
Code

Sampling Matters in Deep Embedding Learning

CompVis/metric-learning-divide-and-conquer • • ICCV 2017

In addition, we show that a simple margin based loss is sufficient to outperform all other loss functions.

5
Paper
Code

Batch DropBlock Network for Person Re-identification and Beyond

daizuozhuo/batch-feature-erasing-network • • ICCV 2019

In this paper, we propose the Batch DropBlock (BDB) Network which is a two branch network composed of a conventional ResNet-50 as the global branch and a feature dropping branch.

5
Paper
Code

SoftTriple Loss: Deep Metric Learning Without Triplet Sampling

idstcv/SoftTriple • • ICCV 2019

The set of triplet constraints has to be sampled within the mini-batch.

5
Paper
Code

12-in-1: Multi-Task Vision and Language Representation Learning

facebookresearch/vilbert-multi-task • • CVPR 2020

Much of vision-and-language research focuses on a small but diverse set of independent tasks and supporting datasets often studied in isolation; however, the visually-grounded language understanding skills required for success at these tasks overlap significantly.

5
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