PyTorchKR Papers

최신 논문

총 185편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2002.07877공식 코드 · Papers with Code

CBIR using features derived by Deep Learning

In a Content Based Image Retrieval (CBIR) System, the task is to retrieve similar images from a large database given a query image. The usual procedure is to extract some useful features from the query image, and retrieve images which have similar set of features. For this purpose, a suitable similarity measure is chosen, and images with high similarity scores are retrieved. Naturally the choice of these features play a very important role in the success of this system, and high level features are required to reduce the semantic gap. In this paper, we propose to use features derived from pre-trained network models from a deep-learning convolution network trained for a large image classification problem. This approach appears to produce vastly superior results for a variety of databases, and it outperforms many contemporary CBIR systems. We analyse the retrieval time of the method, and also propose a pre-clustering of the database based on the above-mentioned features which yields comparable results in a much shorter time in most of the cases.

arXiv:2002.01642

Learning Test-time Augmentation for Content-based Image Retrieval

Off-the-shelf convolutional neural network features achieve outstanding results in many image retrieval tasks. However, their invariance to target data is pre-defined by the network architecture and training data. Existing image retrieval approaches require fine-tuning or modification of pre-trained networks to adapt to variations unique to the target data. In contrast, our method enhances the invariance of off-the-shelf features by aggregating features extracted from images augmented at test-time, with augmentations guided by a policy learned through reinforcement learning. The learned policy assigns different magnitudes and weights to the selected transformations, which are selected from a list of image transformations. Policies are evaluated using a metric learning protocol to learn the optimal policy. The model converges quickly and the cost of each policy iteration is minimal as we propose an off-line caching technique to greatly reduce the computational cost of extracting features from augmented images. Experimental results on large trademark retrieval (METU trademark dataset) and landmark retrieval (ROxford5k and RParis6k scene datasets) tasks show that the learned ensemble of transformations is highly effective for improving performance, and is practical, and transferable.

arXiv:2001.10590

An Effective Automatic Image Annotation Model Via Attention Model and Data Equilibrium

Nowadays, a huge number of images are available. However, retrieving a required image for an ordinary user is a challenging task in computer vision systems. During the past two decades, many types of research have been introduced to improve the performance of the automatic annotation of images, which are traditionally focused on content-based image retrieval. Although, recent research demonstrates that there is a semantic gap between content-based image retrieval and image semantics understandable by humans. As a result, existing research in this area has caused to bridge the semantic gap between low-level image features and high-level semantics. The conventional method of bridging the semantic gap is through the automatic image annotation (AIA) that extracts semantic features using machine learning techniques. In this paper, we propose a novel AIA model based on the deep learning feature extraction method. The proposed model has three phases, including a feature extractor, a tag generator, and an image annotator. First, the proposed model extracts automatically the high and low-level features based on dual-tree continues wavelet transform (DT-CWT), singular value decomposition, distribution of color ton, and the deep neural network. Moreover, the tag generator balances the dictionary of the annotated keywords by a new log-entropy auto-encoder (LEAE) and then describes these keywords by word embedding. Finally, the annotator works based on the long-short-term memory (LSTM) network in order to obtain the importance degree of specific features of the image. The experiments conducted on two benchmark datasets confirm that the superiority of the proposed model compared to the previous models in terms of performance criteria.

arXiv:2001.06372

BigEarthNet Dataset with A New Class-Nomenclature for Remote Sensing Image Understanding

This paper presents BigEarthNet that is a large-scale Sentinel-2 multispectral image dataset with a new class nomenclature to advance deep learning (DL) studies in remote sensing (RS). BigEarthNet is made up of 590,326 image patches annotated with multi-labels provided by the CORINE Land Cover (CLC) map of 2018 based on its most thematic detailed Level-3 class nomenclature. Initial research demonstrates that some CLC classes are challenging to be accurately described by considering only Sentinel-2 images. To increase the effectiveness of BigEarthNet, in this paper we introduce an alternative class-nomenclature to allow DL models for better learning and describing the complex spatial and spectral information content of the Sentinel-2 images. This is achieved by interpreting and arranging the CLC Level-3 nomenclature based on the properties of Sentinel-2 images in a new nomenclature of 19 classes. Then, the new class-nomenclature of BigEarthNet is used within state-of-the-art DL models in the context of multi-label classification. Results show that the models trained from scratch on BigEarthNet outperform those pre-trained on ImageNet, especially in relation to some complex classes including agriculture, other vegetated and natural environments. All DL models are made publicly available at http://bigearth.net/#downloads, offering an important resource to guide future progress on RS image analysis.

arXiv:1912.01824

Efficient feature embedding of 3D brain MRI images for content-based image retrieval with deep metric learning

Increasing numbers of MRI brain scans, improvements in image resolution, and advancements in MRI acquisition technology are causing significant increases in the demand for and burden on radiologists' efforts in terms of reading and interpreting brain MRIs. Content-based image retrieval (CBIR) is an emerging technology for reducing this burden by supporting the reading of medical images. High dimensionality is a major challenge in developing a CBIR system that is applicable for 3D brain MRIs. In this study, we propose a system called disease-oriented data concentration with metric learning (DDCML). In DDCML, we introduce deep metric learning to a 3D convolutional autoencoder (CAE). Our proposed DDCML scheme achieves a high dimensional compression rate (4096:1) while preserving the disease-related anatomical features that are important for medical image classification. The low-dimensional representation obtained by DDCML improved the clustering performance by 29.1\% compared to plain 3D-CAE in terms of discriminating Alzheimer's disease patients from healthy subjects, and successfully reproduced the relationships of the severity of disease categories that were not included in the training.

arXiv:1911.11379

Content-based image retrieval speedup

Content-based image retrieval (CBIR) is a task of retrieving images from their contents. Since retrieval process is a time-consuming task in large image databases, acceleration methods can be very useful. This paper presents a novel method to speed up CBIR systems. In the proposed method, first Zernike moments are extracted from query image and an interval is calculated for that query. Images in database which are out of the interval are ignored in retrieval process. Therefore, a database reduction occurs before retrieval which leads to speed up. It is shown that in reduced database, relevant images to query image are preserved and irrelevant images are throwed away. Therefore, the proposed method speed up retrieval process and preserve CBIR accuracy, simultaneously.

arXiv:1911.11066

Crawler for Image Acquisition from World Wide Web

Due to the advancement in computer communication and storage technologies, large amount of image data is available on World Wide Web (WWW). In order to locate a particular set of images the available search engines may be used with the help of keywords. Here, the filtering of unwanted data is not done. For the purpose of retrieving relevant images with appropriate keyword(s) an image crawler is designed and implemented. Here, keyword(s) are submitted as query and with the help of sender engine, images are downloaded along with metadata like URL, filename, file size, file access date and time etc.,. Later, with the help of URL, images already present in repository and newly downloaded are compared for uniqueness. Only unique URLs are in turn considered and stored in repository. The images in the repository are used to build novel Content Based Image Retrieval (CBIR) system in future. This repository may be used for various purposes. This image crawler tool is useful in building image datasets which can be used by any CBIR system for training and testing purposes.

arXiv:1910.05996

A unified framework of predicting binary interestingness of images based on discriminant correlation analysis and multiple kernel learning

In the modern content-based image retrieval systems, there is an increasingly interest in constructing a computationally effective model to predict the interestingness of images since the measure of image interestingness could improve the human-centered search satisfaction and the user experience in different applications. In this paper, we propose a unified framework to predict the binary interestingness of images based on discriminant correlation analysis (DCA) and multiple kernel learning (MKL) techniques. More specially, on the one hand, to reduce feature redundancy in describing the interestingness cues of images, the DCA or multi-set discriminant correlation analysis (MDCA) technique is adopted to fuse multiple feature sets of the same type for individual cues by taking into account the class structure among the samples involved to describe the three classical interestingness cues, unusualness,aesthetics as well as general preferences, with three sets of compact and representative features; on the other hand, to make good use of the heterogeneity from the three sets of high-level features for describing the interestingness cues, the SimpleMKL method is employed to enhance the generalization ability of the built model for the task of the binary interestingness classification. Experimental results on the publicly-released interestingness prediction data set have demonstrated the rationality and effectiveness of the proposed framework in the binary prediction of image interestingness where we have conducted several groups of comparative studies across different interestingness feature combinations, different interestingness cues, as well as different feature types for the three interestingness cues.

arXiv:1909.09722

Content-based image retrieval using Mix histogram

This paper presents a new method to extract image low-level features, namely mix histogram (MH), for content-based image retrieval. Since color and edge orientation features are important visual information which help the human visual system percept and discriminate different images, this method extracts and integrates color and edge orientation information in order to measure similarity between different images. Traditional color histograms merely focus on the global distribution of color in the image and therefore fail to extract other visual features. The MH is attempting to overcome this problem by extracting edge orientations as well as color feature. The unique characteristic of the MH is that it takes into consideration both color and edge orientation information in an effective manner. Experimental results show that it outperforms many existing methods which were originally developed for image retrieval purposes.

arXiv:1909.09420

Deep Aggregation of Regional Convolutional Activations for Content Based Image Retrieval

One of the key challenges of deep learning based image retrieval remains in aggregating convolutional activations into one highly representative feature vector. Ideally, this descriptor should encode semantic, spatial and low level information. Even though off-the-shelf pre-trained neural networks can already produce good representations in combination with aggregation methods, appropriate fine tuning for the task of image retrieval has shown to significantly boost retrieval performance. In this paper, we present a simple yet effective supervised aggregation method built on top of existing regional pooling approaches. In addition to the maximum activation of a given region, we calculate regional average activations of extracted feature maps. Subsequently, weights for each of the pooled feature vectors are learned to perform a weighted aggregation to a single feature vector. Furthermore, we apply our newly proposed NRA loss function for deep metric learning to fine tune the backbone neural network and to learn the aggregation weights. Our method achieves state-of-the-art results for the INRIA Holidays data set and competitive results for the Oxford Buildings and Paris data sets while reducing the training time significantly.

arXiv:1909.08866

Challenging deep image descriptors for retrieval in heterogeneous iconographic collections

This article proposes to study the behavior of recent and efficient state-of-the-art deep-learning based image descriptors for content-based image retrieval, facing a panel of complex variations appearing in heterogeneous image datasets, in particular in cultural collections that may involve multi-source, multi-date and multi-view Permission to make digital

arXiv:1909.00741

VISIR: Visual and Semantic Image Label Refinement

The social media explosion has populated the Internet with a wealth of images. There are two existing paradigms for image retrieval: 1) content-based image retrieval (CBIR), which has traditionally used visual features for similarity search (e.g., SIFT features), and 2) tag-based image retrieval (TBIR), which has relied on user tagging (e.g., Flickr tags). CBIR now gains semantic expressiveness by advances in deep-learning-based detection of visual labels. TBIR benefits from query-and-click logs to automatically infer more informative labels. However, learning-based tagging still yields noisy labels and is restricted to concrete objects, missing out on generalizations and abstractions. Click-based tagging is limited to terms that appear in the textual context of an image or in queries that lead to a click. This paper addresses the above limitations by semantically refining and expanding the labels suggested by learning-based object detection. We consider the semantic coherence between the labels for different objects, leverage lexical and commonsense knowledge, and cast the label assignment into a constrained optimization problem solved by an integer linear program. Experiments show that our method, called VISIR, improves the quality of the state-of-the-art visual labeling tools like LSDA and YOLO.

arXiv:1908.09300

A Comparison of CNN and Classic Features for Image Retrieval

Feature detectors and descriptors have been successfully used for various computer vision tasks, such as video object tracking and content-based image retrieval. Many methods use image gradients in different stages of the detection-description pipeline to describe local image structures. Recently, some, or all, of these stages have been replaced by convolutional neural networks (CNNs), in order to increase their performance. A detector is defined as a selection problem, which makes it more challenging to implement as a CNN. They are therefore generally defined as regressors, converting input images to score maps and keypoints can be selected with non-maximum suppression. This paper discusses and compares several recent methods that use CNNs for keypoint detection. Experiments are performed both on the CNN based approaches, as well as a selection of conventional methods. In addition to qualitative measures defined on keypoints and descriptors, the bag-of-words (BoW) model is used to implement an image retrieval application, in order to determine how the methods perform in practice. The results show that each type of features are best in different contexts.

arXiv:1908.06896

Genetic Algorithms for the Optimization of Diffusion Parameters in Content-Based Image Retrieval

Several computer vision and artificial intelligence projects are nowadays exploiting the manifold data distribution using, e.g., the diffusion process. This approach has produced dramatic improvements on the final performance thanks to the application of such algorithms to the kNN graph. Unfortunately, this recent technique needs a manual configuration of several parameters, thus it is not straightforward to find the best configuration for each dataset. Moreover, the brute-force approach is computationally very demanding when used to optimally set the parameters of the diffusion approach. We propose to use genetic algorithms to find the optimal setting of all the diffusion parameters with respect to retrieval performance for each different dataset. Our approach is faster than others used as references (brute-force, random-search and PSO). A comparison with these methods has been made on three public image datasets: Oxford5k, Paris6k and Oxford105k.

arXiv:1908.03361공식 코드 · Papers with Code

Enhancing Flood Impact Analysis using Interactive Retrieval of Social Media Images

The analysis of natural disasters such as floods in a timely manner often suffers from limited data due to a coarse distribution of sensors or sensor failures. This limitation could be alleviated by leveraging information contained in images of the event posted on social media platforms, so-called "Volunteered Geographic Information (VGI)". To save the analyst from the need to inspect all images posted online manually, we propose to use content-based image retrieval with the possibility of relevance feedback for retrieving only relevant images of the event to be analyzed. To evaluate this approach, we introduce a new dataset of 3,710 flood images, annotated by domain experts regarding their relevance with respect to three tasks (determining the flooded area, inundation depth, water pollution). We compare several image features and relevance feedback methods on that dataset, mixed with 97,085 distractor images, and are able to improve the precision among the top 100 retrieval results from 55% with the baseline retrieval to 87% after 5 rounds of feedback.

arXiv:1908.01505

A Fast Content-Based Image Retrieval Method Using Deep Visual Features

Fast and scalable Content-Based Image Retrieval using visual features is required for document analysis, Medical image analysis, etc. in the present age. Convolutional Neural Network (CNN) activations as features achieved their outstanding performance in this area. Deep Convolutional representations using the softmax function in the output layer are also ones among visual features. However, almost all the image retrieval systems hold their index of visual features on main memory in order to high responsiveness, limiting their applicability for big data applications. In this paper, we propose a fast calculation method of cosine similarity with L2 norm indexed in advance on Elasticsearch. We evaluate our approach with ImageNet Dataset and VGG-16 pre-trained model. The evaluation results show the effectiveness and efficiency of our proposed method.

arXiv:1907.09404

Deep Learning Approaches for Image Retrieval and Pattern Spotting in Ancient Documents

This paper describes two approaches for content-based image retrieval and pattern spotting in document images using deep learning. The first approach uses a pre-trained CNN model to cope with the lack of training data, which is fine-tuned to achieve a compact yet discriminant representation of queries and image candidates. The second approach uses a Siamese Convolution Neural Network trained on a previously prepared subset of image pairs from the ImageNet dataset to provide the similarity-based feature maps. In both methods, the learned representation scheme considers feature maps of different sizes which are evaluated in terms of retrieval performance. A robust experimental protocol using two public datasets (Tobacoo-800 and DocExplore) has shown that the proposed methods compare favorably against state-of-the-art document image retrieval and pattern spotting methods.

arXiv:1907.03537

Linking Art through Human Poses

We address the discovery of composition transfer in artworks based on their visual content. Automated analysis of large art collections, which are growing as a result of art digitization among museums and galleries, is an important tool for art history and assists cultural heritage preservation. Modern image retrieval systems offer good performance on visually similar artworks, but fail in the cases of more abstract composition transfer. The proposed approach links artworks through a pose similarity of human figures depicted in images. Human figures are the subject of a large fraction of visual art from middle ages to modernity and their distinctive poses were often a source of inspiration among artists. The method consists of two steps -- fast pose matching and robust spatial verification. We experimentally show that explicit human pose matching is superior to standard content-based image retrieval methods on a manually annotated art composition transfer dataset.

arXiv:1907.02821

Benchmarking unsupervised near-duplicate image detection

Unsupervised near-duplicate detection has many practical applications ranging from social media analysis and web-scale retrieval, to digital image forensics. It entails running a threshold-limited query on a set of descriptors extracted from the images, with the goal of identifying all possible near-duplicates, while limiting the false positives due to visually similar images. Since the rate of false alarms grows with the dataset size, a very high specificity is thus required, up to $1 - 10^{-9}$ for realistic use cases; this important requirement, however, is often overlooked in literature. In recent years, descriptors based on deep convolutional neural networks have matched or surpassed traditional feature extraction methods in content-based image retrieval tasks. To the best of our knowledge, ours is the first attempt to establish the performance range of deep learning-based descriptors for unsupervised near-duplicate detection on a range of datasets, encompassing a broad spectrum of near-duplicate definitions. We leverage both established and new benchmarks, such as the Mir-Flick Near-Duplicate (MFND) dataset, in which a known ground truth is provided for all possible pairs over a general, large scale image collection. To compare the specificity of different descriptors, we reduce the problem of unsupervised detection to that of binary classification of near-duplicate vs. not-near-duplicate images. The latter can be conveniently characterized using Receiver Operating Curve (ROC). Our findings in general favor the choice of fine-tuning deep convolutional networks, as opposed to using off-the-shelf features, but differences at high specificity settings depend on the dataset and are often small. The best performance was observed on the MFND benchmark, achieving 96\% sensitivity at a false positive rate of $1.43 \times 10^{-6}$.

arXiv:1906.01062

A Curated Image Parameter Dataset from Solar Dynamics Observatory Mission

We provide a large image parameter dataset extracted from the Solar Dynamics Observatory (SDO) mission's AIA instrument, for the period of January 2011 through the current date, with the cadence of six minutes, for nine wavelength channels. The volume of the dataset for each year is just short of 1 TiB. Towards achieving better results in the region classification of active regions and coronal holes, we improve upon the performance of a set of ten image parameters, through an in depth evaluation of various assumptions that are necessary for calculation of these image parameters. Then, where possible, a method for finding an appropriate settings for the parameter calculations was devised, as well as a validation task to show our improved results. In addition, we include comparisons of JP2 and FITS image formats using supervised classification models, by tuning the parameters specific to the format of the images from which they are extracted, and specific to each wavelength. The results of these comparisons show that utilizing JP2 images, which are significantly smaller files, is not detrimental to the region classification task that these parameters were originally intended for. Finally, we compute the tuned parameters on the AIA images and provide a public API (http://dmlab.cs.gsu.edu/dmlabapi) to access the dataset. This dataset can be used in a range of studies on AIA images, such as content-based image retrieval or tracking of solar events, where dimensionality reduction on the images is necessary for feasibility of the tasks.