Browse > Computer Vision > Image Retrieval

Image Retrieval

79 papers with code · Computer Vision

Image retrieval systems aim to find similar images to a query image among an image dataset.

State-of-the-art leaderboards

Greatest papers with code

Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking

CVPR 2018 tensorflow/models

In particular, annotation errors, the size of the dataset, and the level of challenge are addressed: new annotation for both datasets is created with an extra attention to the reliability of the ground truth. An extensive comparison of the state-of-the-art methods is performed on the new benchmark.


Large-Scale Image Retrieval with Attentive Deep Local Features

ICCV 2017 tensorflow/models

We propose an attentive local feature descriptor suitable for large-scale image retrieval, referred to as DELF (DEep Local Feature). This framework can be used for image retrieval as a drop-in replacement for other keypoint detectors and descriptors, enabling more accurate feature matching and geometric verification.


VGGFace2: A dataset for recognising faces across pose and age

23 Oct 2017deepinsight/insightface

The dataset was collected with three goals in mind: (i) to have both a large number of identities and also a large number of images for each identity; (ii) to cover a large range of pose, age and ethnicity; and (iii) to minimize the label noise. Finally, using the models trained on these datasets, we demonstrate state-of-the-art performance on all the IARPA Janus face recognition benchmarks, e.g. IJB-A, IJB-B and IJB-C, exceeding the previous state-of-the-art by a large margin.


Improving zero-shot learning by mitigating the hubness problem

20 Dec 2014facebookresearch/MUSE

The zero-shot paradigm exploits vector-based word representations extracted from text corpora with unsupervised methods to learn general mapping functions from other feature spaces onto word space, where the words associated to the nearest neighbours of the mapped vectors are used as their linguistic labels. We show that the neighbourhoods of the mapped elements are strongly polluted by hubs, vectors that tend to be near a high proportion of items, pushing their correct labels down the neighbour list.


Learning Deep Representations of Fine-grained Visual Descriptions

CVPR 2016 hanzhanggit/StackGAN-v2

State-of-the-art methods for zero-shot visual recognition formulate learning as a joint embedding problem of images and side information. In these formulations the current best complement to visual features are attributes: manually encoded vectors describing shared characteristics among categories.


Looking at Outfit to Parse Clothing

4 Mar 2017kyamagu/js-segment-annotator

This paper extends fully-convolutional neural networks (FCN) for the clothing parsing problem. Clothing parsing requires higher-level knowledge on clothing semantics and contextual cues to disambiguate fine-grained categories.


CNN Features off-the-shelf: an Astounding Baseline for Recognition

23 Mar 2014baldassarreFe/deep-koalarization

We report on a series of experiments conducted for different recognition tasks using the publicly available code and model of the \overfeat network which was trained to perform object classification on ILSVRC13. We use features extracted from the \overfeat network as a generic image representation to tackle the diverse range of recognition tasks of object image classification, scene recognition, fine grained recognition, attribute detection and image retrieval applied to a diverse set of datasets.


Fine-tuning CNN Image Retrieval with No Human Annotation

3 Nov 2017filipradenovic/cnnimageretrieval-pytorch

In this work, we propose to fine-tune CNNs for image retrieval on a large collection of unordered images in a fully automated manner. We show that both hard-positive and hard-negative examples, selected by exploiting the geometry and the camera positions available from the 3D models, enhance the performance of particular-object retrieval.


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

8 Apr 2016filipradenovic/cnnimageretrieval-pytorch

Convolutional Neural Networks (CNNs) achieve state-of-the-art performance in many computer vision tasks. However, this achievement is preceded by extreme manual annotation in order to perform either training from scratch or fine-tuning for the target task.


Deep Exemplar-based Colorization

17 Jul 2018msracver/Deep-Exemplar-based-Colorization

More importantly, as opposed to other learning-based colorization methods, our network allows the user to achieve customizable results by simply feeding different references. The colorization can be performed fully automatically by simply picking the top reference suggestion.