Accurate Image Retrieval With Unsupervised 2-Stage k-NN Re-Ranking

2018 ◽  
pp. 1726-1745
Author(s):  
Dawei Li ◽  
Mooi Choo Chuah
Keyword(s):  
Image Retrieval ◽  
Large Scale ◽  
Ground Truth ◽  
Confidence Score ◽  
Image Feature ◽  
Superior Performance ◽  
Ranking Algorithm ◽  
Ranking List ◽  
Image Patches ◽  
Benchmark Datasets

Many state-of-the-art image retrieval systems include a re-ranking step to refine the suggested initial ranking list so as to improve the retrieval accuracy. In this paper, we present a novel 2-stage k-NN re-ranking algorithm. In stage one, we generate an expanded list of candidate database images for re-ranking so that lower ranked ground truth images will be included and re-ranked. In stage two, we re-rank the list of candidate images using a confidence score which is calculated based on, rRBO, a new proposed ranking list similarity measure. In addition, we propose the rLoCATe image feature, which captures robust color and texture information on salient image patches, and shows superior performance in the image retrieval task. We evaluate the proposed re-ranking algorithm on various initial ranking lists created using both SIFT and rLoCATe on two popular benchmark datasets along with a large-scale one million distraction dataset. The results show that our proposed algorithm is not sensitive for different parameter configurations and it outperforms existing k-NN re-ranking methods.

Accurate Image Retrieval with Unsupervised 2-Stage k-NN Re-Ranking

2016 ◽  
Vol 7 (1) ◽  
pp. 41-59
Author(s):  
Dawei Li ◽  
Mooi Choo Chuah
Keyword(s):  
Image Retrieval ◽  
Large Scale ◽  
Ground Truth ◽  
Confidence Score ◽  
Image Feature ◽  
Superior Performance ◽  
Ranking Algorithm ◽  
Retrieval Task ◽  
Ranking List ◽  
Benchmark Datasets

Many state-of-the-art image retrieval systems include a re-ranking step to refine the suggested initial ranking list so as to improve the retrieval accuracy. In this paper, we present a novel 2-stage k-NN re-ranking algorithm. In stage one, we generate an expanded list of candidate database images for re-ranking so that lower ranked ground truth images will be included and re-ranked. In stage two, we re-rank the list of candidate images using a confidence score which is calculated based on, rRBO, a new proposed ranking list similarity measure. In addition, we propose the rLoCATe image feature, which captures robust color and texture information on salient image patches, and shows superior performance in the image retrieval task. We evaluate the proposed re-ranking algorithm on various initial ranking lists created using both SIFT and rLoCATe on two popular benchmark datasets along with a large-scale one million distraction dataset. The results show that our proposed algorithm is not sensitive for different parameter configurations and it outperforms existing k-NN re-ranking methods.

scholarly journals An Advanced Relevance Feedback Method to Improve Performance of CBIR using Convolutional Neural Network and Comprehensive Values

2019 ◽  
Vol 9 (2) ◽  
pp. 5427-5438
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Image Retrieval ◽  
Convolutional Neural Network ◽  
Large Scale ◽  
Activation Function ◽  
Image Feature ◽  
Similarity Measurement ◽  
Query Image ◽  
Image Production

Content-Based Image Retrieval (CBIR) is extensively used technique for image retrieval from large image databases. However, users are not satisfied with the conventional image retrieval techniques. In addition, the advent of web development and transmission networks, the number of images available to users continues to increase. Therefore, a permanent and considerable digital image production in many areas takes place. Quick access to the similar images of a given query image from this extensive collection of images pose great challenges and require proficient techniques. From query by image to retrieval of relevant images, CBIR has key phases such as feature extraction, similarity measurement, and retrieval of relevant images. However, extracting the features of the images is one of the important steps. Recently Convolutional Neural Network (CNN) shows good results in the field of computer vision due to the ability of feature extraction from the images. Alex Net is a classical Deep CNN for image feature extraction. We have modified the Alex Net Architecture with a few changes and proposed a novel framework to improve its ability for feature extraction and for similarity measurement. The proposal approach optimizes Alex Net in the aspect of pooling layer. In particular, average pooling is replaced by max-avg pooling and the non-linear activation function Maxout is used after every Convolution layer for better feature extraction. This paper introduces CNN for features extraction from images in CBIR system and also presents Euclidean distance along with the Comprehensive Values for better results. The proposed framework goes beyond image retrieval, including the large-scale database. The performance of the proposed work is evaluated using precision. The proposed work show better results than existing works.

A Combination of Spatial Pyramid and Inverted Index for Large-Scale Image Retrieval

2018 ◽  
pp. 1307-1321
Author(s):  
Vinh-Tiep Nguyen ◽  
Thanh Duc Ngo ◽  
Minh-Triet Tran ◽  
Duy-Dinh Le ◽  
Duc Anh Duong
Keyword(s):  
Image Retrieval ◽  
Large Scale ◽  
Spatial Information ◽  
Real Life ◽  
Inverted Index ◽  
Bag Of Words ◽  
Visual Words ◽  
Benchmark Datasets ◽  
Large Scale Image Retrieval ◽  
Inverted Indexing

Large-scale image retrieval has been shown remarkable potential in real-life applications. The standard approach is based on Inverted Indexing, given images are represented using Bag-of-Words model. However, one major limitation of both Inverted Index and Bag-of-Words presentation is that they ignore spatial information of visual words in image presentation and comparison. As a result, retrieval accuracy is decreased. In this paper, the authors investigate an approach to integrate spatial information into Inverted Index to improve accuracy while maintaining short retrieval time. Experiments conducted on several benchmark datasets (Oxford Building 5K, Oxford Building 5K+100K and Paris 6K) demonstrate the effectiveness of our proposed approach.

A Combination of Spatial Pyramid and Inverted Index for Large-Scale Image Retrieval

2015 ◽  
Vol 6 (2) ◽  
pp. 37-51 ◽  
Author(s):  
Vinh-Tiep Nguyen ◽  
Thanh Duc Ngo ◽  
Minh-Triet Tran ◽  
Duy-Dinh Le ◽  
Duc Anh Duong
Keyword(s):  
Image Retrieval ◽  
Large Scale ◽  
Spatial Information ◽  
Real Life ◽  
Inverted Index ◽  
Bag Of Words ◽  
Visual Words ◽  
Benchmark Datasets ◽  
Large Scale Image Retrieval ◽  
Inverted Indexing

Large-scale image retrieval has been shown remarkable potential in real-life applications. The standard approach is based on Inverted Indexing, given images are represented using Bag-of-Words model. However, one major limitation of both Inverted Index and Bag-of-Words presentation is that they ignore spatial information of visual words in image presentation and comparison. As a result, retrieval accuracy is decreased. In this paper, the authors investigate an approach to integrate spatial information into Inverted Index to improve accuracy while maintaining short retrieval time. Experiments conducted on several benchmark datasets (Oxford Building 5K, Oxford Building 5K+100K and Paris 6K) demonstrate the effectiveness of our proposed approach.

scholarly journals Logo-2K+: A Large-Scale Logo Dataset for Scalable Logo Classification

2020 ◽  
Vol 34 (04) ◽  
pp. 6194-6201
Author(s):  
Jing Wang ◽  
Weiqing Min ◽  
Sujuan Hou ◽  
Shengnan Ma ◽  
Yuanjie Zheng ◽  
...  
Keyword(s):  
Image Recognition ◽  
Real World ◽  
Large Scale ◽  
Data Augmentation ◽  
Ground Truth ◽  
Classification Task ◽  
The Real ◽  
Product Recommendation ◽  
Contextual Advertising ◽  
Benchmark Datasets

Logo classification has gained increasing attention for its various applications, such as copyright infringement detection, product recommendation and contextual advertising. Compared with other types of object images, the real-world logo images have larger variety in logo appearance and more complexity in their background. Therefore, recognizing the logo from images is challenging. To support efforts towards scalable logo classification task, we have curated a dataset, Logo-2K+, a new large-scale publicly available real-world logo dataset with 2,341 categories and 167,140 images. Compared with existing popular logo datasets, such as FlickrLogos-32 and LOGO-Net, Logo-2K+ has more comprehensive coverage of logo categories and larger quantity of logo images. Moreover, we propose a Discriminative Region Navigation and Augmentation Network (DRNA-Net), which is capable of discovering more informative logo regions and augmenting these image regions for logo classification. DRNA-Net consists of four sub-networks: the navigator sub-network first selected informative logo-relevant regions guided by the teacher sub-network, which can evaluate its confidence belonging to the ground-truth logo class. The data augmentation sub-network then augments the selected regions via both region cropping and region dropping. Finally, the scrutinizer sub-network fuses features from augmented regions and the whole image for logo classification. Comprehensive experiments on Logo-2K+ and other three existing benchmark datasets demonstrate the effectiveness of proposed method. Logo-2K+ and the proposed strong baseline DRNA-Net are expected to further the development of scalable logo image recognition, and the Logo-2K+ dataset can be found at https://github.com/msn199959/Logo-2k-plus-Dataset.

scholarly journals No-Reference Image Quality Assessment with Reinforcement Recursive List-Wise Ranking

2019 ◽  
Vol 33 ◽  
pp. 8336-8343
Author(s):  
Jie Gu ◽  
Gaofeng Meng ◽  
Cheng Da ◽  
Shiming Xiang ◽  
Chunhong Pan
Keyword(s):  
Image Quality ◽  
Quality Assessment ◽  
Image Quality Assessment ◽  
Ground Truth ◽  
Superior Performance ◽  
Reference Image ◽  
Model Parameters ◽  
Ranking Problem ◽  
Ranking List ◽  
Markov Decision

Opinion-unaware no-reference image quality assessment (NR-IQA) methods have received many interests recently because they do not require images with subjective scores for training. Unfortunately, it is a challenging task, and thus far no opinion-unaware methods have shown consistently better performance than the opinion-aware ones. In this paper, we propose an effective opinion-unaware NR-IQA method based on reinforcement recursive list-wise ranking. We formulate the NR-IQA as a recursive list-wise ranking problem which aims to optimize the whole quality ordering directly. During training, the recursive ranking process can be modeled as a Markov decision process (MDP). The ranking list of images can be constructed by taking a sequence of actions, and each of them refers to selecting an image for a specific position of the ranking list. Reinforcement learning is adopted to train the model parameters, in which no ground-truth quality scores or ranking lists are necessary for learning. Experimental results demonstrate the superior performance of our approach compared with existing opinion-unaware NR-IQA methods. Furthermore, our approach can compete with the most effective opinion-aware methods. It improves the state-of-the-art by over 2% on the CSIQ benchmark and outperforms most compared opinion-aware models on TID2013.

scholarly journals Discriminative Deep Hashing for Scalable Face Image Retrieval

2017 ◽  
Author(s):  
Jie Lin ◽  
Zechao Li ◽  
Jinhui Tang
Keyword(s):  
Image Retrieval ◽  
Large Scale ◽  
State Of The Art ◽  
Face Image ◽  
Superior Performance ◽  
Prediction Errors ◽  
Unified Framework ◽  
Multi Scale ◽  
Deep Hashing ◽  
Hash Codes

With the explosive growth of images containing faces, scalable face image retrieval has attracted increasing attention. Due to the amazing effectiveness, deep hashing has become a popular hashing method recently. In this work, we propose a new Discriminative Deep Hashing (DDH) network to learn discriminative and compact hash codes for large-scale face image retrieval. The proposed network incorporates the end-to-end learning, the divide-and-encode module and the desired discrete code learning into a unified framework. Specifically, a network with a stack of convolution-pooling layers is proposed to extract multi-scale and robust features by merging the outputs of the third max pooling layer and the fourth convolutional layer. To reduce the redundancy among hash codes and the network parameters simultaneously, a divide-and-encode module to generate compact hash codes. Moreover, a loss function is introduced to minimize the prediction errors of the learned hash codes, which can lead to discriminative hash codes. Extensive experiments on two datasets demonstrate that the proposed method achieves superior performance compared with some state-of-the-art hashing methods.

scholarly journals Challenges in Peptide-Spectrum Matching: a Robust and Reproducible Statistical Framework for Removing Low-Accuracy, High-Scoring Hits

2019 ◽  
Author(s):  
Shane L. Hubler ◽  
Praveen Kumar ◽  
Subina Mehta ◽  
Caleb Easterly ◽  
James E. Johnson ◽  
...  
Keyword(s):  
Large Scale ◽  
Method Development ◽  
Ground Truth ◽  
Shotgun Proteomics ◽  
Confidence Score ◽  
Reference Database ◽  
Confidence Measure ◽  
Statistical Framework ◽  
Single Organism ◽  
Spectrum Matching

AbstractWorkflows for large-scale (MS)-based shotgun proteomics can potentially lead to costly errors in the form of incorrect peptide spectrum matches (PSMs). To improve robustness of these workflows, we have investigated the use of the precursor mass discrepancy (PMD) to detect and filter potentially false PSMs that have, nonetheless, a high confidence score. We identified and addressed three cases of unexpected bias in PMD results: time of acquisition within a LC-MS run, decoy PSMs, and length of peptide. We created a post-analysis Bayesian confidence measure based on score and PMD, called PMD-FDR. We tested PMD-FDR on four datasets across three types of MS-based proteomics projects: standard (single organism; reference database), proteogenomics (single organism; customized genomic-based database plus reference), and metaproteomics (microorganism community; customized conglomerate database). On a ground truth dataset and other representative data, PMD-FDR was able to detect 60-80% of likely incorrect PSMs (false-hits) while losing only 5% of correct PSMs (true-hits). PMD-FDR can also be used to evaluate data quality for results generated within different experimental PSM-generating workflows, assisting in method development. Going forward, PMD-FDR should provide detection of high-scoring but likely false-hits, aiding applications which rely heavily on accurate PSMs, such as proteogenomics and metaproteomics.

scholarly journals Multiproxies Adaptive Distribution Loss with Weakly Supervised Feature Aggregation for Fine-Grained Retrieval

2021 ◽  
Vol 2021 ◽  
pp. 1-16
Author(s):  
Hongwei Zhao ◽  
Danyang Zhang ◽  
Jiaxin Wu ◽  
Pingping Liu
Keyword(s):  
Image Retrieval ◽  
Image Feature ◽  
Cluster Center ◽  
Unified Framework ◽  
Retrieval Method ◽  
Fine Grained ◽  
Feature Aggregation ◽  
Benchmark Datasets ◽  
Weakly Supervised ◽  
Representative Image

Fine-grained retrieval is one of the complex problems in computer vision. Compared with general content-based image retrieval, fine-grained image retrieval faces more difficult challenges. In fine-grained image retrieval tasks, all classes belong to a subclass of a meta-class, so there will be small interclass variance and large intraclass variance. In order to solve this problem, in this paper, we propose a fine-grained retrieval method to improve loss and feature aggregation, which can achieve better retrieval results under a unified framework. Firstly, we propose a novel multiproxies adaptive distribution loss which can better characterize the intraclass variations and the degree of dispersion of each cluster center. Secondly, we propose a weakly supervised feature aggregation method based on channel weighting, which distinguishes the importance of different feature channels to obtain more representative image feature descriptors. We verify the performance of our proposed method on the universal benchmark datasets such as CUB200-2011 and Stanford Dog. Higher Recall@K demonstrates the advantage of our proposed method over the state of the art.

scholarly journals Deep Feature Learning with Manifold Embedding for Robust Image Retrieval

Algorithms ◽  
2020 ◽  
Vol 13 (12) ◽  
pp. 318
Author(s):  
Xin Chen ◽  
Ying Li
Keyword(s):  
Image Retrieval ◽  
Euclidean Distance ◽  
Large Scale ◽  
Training Image ◽  
Fine Tuning ◽  
Image Feature ◽  
Similarity Measurement ◽  
Local Geometry ◽  
Robust Image ◽  
Image Pairs

Conventionally, the similarity between two images is measured by the easy-calculating Euclidean distance between their corresponding image feature representations for image retrieval. However, this kind of direct similarity measurement ignores the local geometry structure of the intrinsic data manifold, which is not discriminative enough for robust image retrieval. Some works have proposed to tackle this problem by re-ranking with manifold learning. While benefiting better performance, algorithms of this category suffer from non-trivial computational complexity, which is unfavorable for its application to large-scale retrieval tasks. To address the above problems, in this paper, we propose to learn a robust feature embedding with the guidance of manifold relationships. Specifically, the manifold relationship is used to guide the automatic selection of training image pairs. A fine-tuning network with those selected image pairs transfers such manifold relationships into the fine-tuned feature embedding. With the fine-tuned feature embedding, the Euclidean distance can be directly used to measure the pairwise similarity between images, where the manifold structure is implicitly embedded. Thus, we maintain both the efficiency of Euclidean distance-based similarity measurement and the effectiveness of manifold information in the new feature embedding. Extensive experiments on three benchmark datasets demonstrate the robustness of our proposed method, where our approach significantly outperforms the baselines and exceeds or is comparable to the state-of-the-art methods.

Sign in / Sign up

Export Citation Format

Share Document