Corpus ID: 231718828

Deep Image Retrieval: A Survey

@article{Chen2021DeepIR,
  title={Deep Image Retrieval: A Survey},
  author={Wei Chen and Yang Liu and Weiping Wang and Erwin M. Bakker and Theodoros Georgiou and Paul W. Fieguth and Li Liu and Michael S. Lew},
  journal={ArXiv},
  year={2021},
  volume={abs/2101.11282}
}
In recent years a vast amount of visual content has been generated and shared from various fields, such as social media platforms, medical images, and robotics. This abundance of content creation and sharing has introduced new challenges. In particular, searching databases for similar content, i.e., content based image retrieval (CBIR), is a long-established research area, and more efficient and accurate methods are needed for real time retrieval. Artificial intelligence has made progress in… Expand
DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Features
  • Min Yang, Dongliang He, +5 authors Jizhou Huang
  • Computer Science
  • ArXiv
  • 2021
TLDR
This paper proposes a Deep Orthogonal Local and Global (DOLG) information fusion framework for end-to-end image retrieval that achieves state-of-the-art image retrieval performances on Revisited Oxford and Paris datasets. Expand
Informative and Representative Triplet Selection for Multi-Label Remote Sensing Image Retrieval
TLDR
A novel triplet sampling method in the framework of deep neural networks (DNNs) defined for multilabel RS CBIR problems results in reducing the computational complexity of the training phase of the DNNs without any significant loss on the performance and an increase in learning speed since informative triplets allow fast convergence. Expand
A Visual and VAE Based Hierarchical Indoor Localization Method
TLDR
This paper proposes an unsupervised hierarchical indoor localization framework that integrates an un supervised network variational autoencoder (VAE) with a visual-based Structure-from-Motion (SfM) approach in order to extract global and local features. Expand
Telling the What while Pointing to the Where: Multimodal Queries for Image Retrieval
TLDR
This paper proposes an image retrieval setup with a new form of multimodal queries, where the user simultaneously uses both spoken natural language and mouse traces over an empty canvas to express the characteristics of the desired target image. Expand
Fine-Grained Adversarial Semi-supervised Learning
TLDR
This paper exploits Semi-Supervised Learning (SSL) to increase the amount of training data to improve the performance of Fine-Grained Visual Categorization (FGVC) and has better performance than the only previous approach that examined this problem. Expand
Telling the What while Pointing the Where: Fine-grained Mouse Trace and Language Supervision for Improved Image Retrieval
TLDR
An image retrieval setup where the user simultaneously describes an image using both spoken natural language and mouse traces over an empty canvas to express the characteristics of the desired target image is described. Expand
One-Shot Object Affordance Detection in the Wild
TLDR
A One-Shot Affordance Detection Network (OSAD-Net) that firstly estimates the human action purpose and then transfers it to help detect the common affordance from all candidate images and builds a large-scale Purpose-driven Affordances Dataset v2 (PADv2) by collecting and labeling 30k images. Expand
Differentially Private Supervised Manifold Learning with Applications like Private Image Retrieval
TLDR
A novel differentially private method PrivateMail is presented for supervised manifold learning, the first of its kind to the authors' knowledge, and a novel private geometric embedding scheme is provided for this experimental use case. Expand
PrivateMail: Supervised Manifold Learning of Deep Features With Differential Privacy for Image Retrieval
TLDR
This work proposes a differentially private mechanism called PrivateMail for performing supervised manifold learning, and applies it to the use case of private image retrieval to obtain nearest matches to a client’s target image from a server's database. Expand
EDEN: Deep Feature Distribution Pooling for Saimaa Ringed Seals Pattern Matching
TLDR
A novel feature pooling approach that allow aggregating the local pattern features to get a fixed size embedding vector that incorporate global features by taking into account the spatial distribution of features. Expand
...
1
2
...

References

SHOWING 1-10 OF 176 REFERENCES
DeepIndex for Accurate and Efficient Image Retrieval
TLDR
This work attempts to introduce deep features into inverted index based image retrieval and proposes the DeepIndex framework, which finds the optimal integration of one midlevel deep feature and one high- level deep feature, from two different CNN architectures separately. Expand
Deep Learning for Content-Based Image Retrieval: A Comprehensive Study
TLDR
This paper investigates a framework of deep learning with application to CBIR tasks with an extensive set of empirical studies by examining a state-of-the-art deep learning method (Convolutional Neural Networks) for CBIr tasks under varied settings. Expand
Deep convolutional image retrieval: A general framework
TLDR
The experimental evaluation on six publicly available image retrieval datasets indicates the effectiveness of the proposed Convolutional Neural Network framework in learning more efficient representations for the retrieval task, outperforming other CNN-based retrieval techniques, as well as conventional hand-crafted feature-based approaches. Expand
Semantic content-based image retrieval: A comprehensive study
TLDR
This study presents a detailed overview of the CBIR framework and improvements achieved; including image preprocessing, feature extraction and indexing, system learning, benchmarking datasets, similarity matching, relevance feedback, performance evaluation, and visualization. Expand
SIFT Meets CNN: A Decade Survey of Instance Retrieval
  • L. Zheng, Yi Yang, Q. Tian
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2018
TLDR
A comprehensive survey of instance retrieval over the last decade, presenting milestones in modern instance retrieval, reviews a broad selection of previous works in different categories, and provides insights on the connection between SIFT and CNN-based methods. Expand
Regional Attention Based Deep Feature for Image Retrieval
TLDR
This work builds a simple and effective, contextaware regional attention network that weights an attentive score of a region considering global attentiveness and shows higher accuracy improvement combined over prior methods, when combined with the query expansion method. Expand
Aggregating Local Deep Features for Image Retrieval
TLDR
This paper shows that deep features and traditional hand-engineered features have quite different distributions of pairwise similarities, hence existing aggregation methods have to be carefully re-evaluated and reveals that in contrast to shallow features, the simple aggregation method based on sum pooling provides the best performance for deep convolutional features. Expand
Cross-batch Reference Learning for Deep Classification and Retrieval
TLDR
This work introduces a new idea called cross-batch reference (CBR) to enhance the stochastic-gradient-descent (SGD) training of CNNs, and designs a loss function that is an approximated lower bound of the MAP on the feature layer of the network, which is differentiable and easier for optimization. Expand
Deep Image Retrieval: Learning Global Representations for Image Search
TLDR
This work proposes a novel approach for instance-level image retrieval that produces a global and compact fixed-length representation for each image by aggregating many region-wise descriptors by leveraging a ranking framework and projection weights to build the region features. Expand
Regional deep feature aggregation for image retrieval
TLDR
The proposed method is to find possible candidate regions in an image, extract region descriptors from each region, and match images in a region-by-region manner to adhere to using a pre-trained network without retraining or spatial verification. Expand
...
1
2
3
4
5
...