Download or read book Contributions to Large scale Learning for Image Classification written by Zeynep Akata and published by . This book was released on 2014 with total page 0 pages. Available in PDF, EPUB and Kindle. Book excerpt: Building algorithms that classify images on a large scale is an essential task due to the difficulty in searching massive amount of unlabeled visual data available on the Internet. We aim at classifying images based on their content to simplify the manageability of such large-scale collections. Large-scale image classification is a difficult problem as datasets are large with respect to both the number of images and the number of classes. Some of these classes are fine grained and they may not contain any labeled representatives. In this thesis, we use state-of-the-art image representations and focus on efficient learning methods. Our contributions are (1) a benchmark of learning algorithms for large scale image classification, and (2) a novel learning algorithm based on label embedding for learning with scarce training data. Firstly, we propose a benchmark of learning algorithms for large scale image classification in the fully supervised setting. It compares several objective functions for learning linear classifiers such as one-vs-rest, multiclass, ranking and weighted average ranking using the stochastic gradient descent optimization. The output of this benchmark is a set of recommendations for large-scale learning. We experimentally show that, online learning is well suited for large-scale image classification. With simple data rebalancing, One-vs-Rest performs better than all other methods. Moreover, in online learning, using a small enough step size with respect to the learning rate is sufficient for state-of-the-art performance. Finally, regularization through early stopping results in fast training and a good generalization performance. Secondly, when dealing with thousands of classes, it is difficult to collect sufficient labeled training data for each class. For some classes we might not even have a single training example. We propose a novel algorithm for this zero-shot learning scenario. Our algorithm uses side information, such as attributes to embed classes in a Euclidean space. We also introduce a function to measure the compatibility between an image and a label. The parameters of this function are learned using a ranking objective. Our algorithm outperforms the state-of-the-art for zero-shot learning. It is flexible and can accommodate other sources of side information such as hierarchies. It also allows for a smooth transition from zero-shot to few-shots learning.

Download or read book Methods for Large scale Machine Learning and Computer Vision written by Li Yeqing and published by . This book was released on 2016 with total page 90 pages. Available in PDF, EPUB and Kindle. Book excerpt: With the advance of the Internet and information technology, nowadays people can easily collect and store tremendous amounts of data such as images and videos. Developing machine learning and computer vision to analysis and learn from the gigantic data sets is an interesting yet challenging problem. Inspired by the trend, this thesis focus on developing large-scale machine learning and computer vision techniques for the purpose of handling various kinds of problems on gigantic data sets. With respect to the problem of image classification, we employ the technique of sub-selection, which uses partial observations to efficiently approximate the original high dimensional problems.. We consider the classification models based on sparse representation or collaborative representation. In practical applications, the performance of classification can be affected by problems like misalignment, occlusion and big noises. To deal with these problems, we propose a robust sub-representation method, which can effectively handle these problems with an efficient scheme. With respect to the problem of similarity search, this thesis contribute a novel method for hashing a large number of images. While many researchers have worked on the topic of how to find good hash function for this task, the thesis will propose a new approach to address effciency. In particular, the training step of many existing hash methods relies on computing the Principle Components Analysis (PCA). However, performing PCA on large dataset is time-consuming. The thesis will prove that, under some conditions, the PCA can be computed by using only a small part of the data. With the theoretical guarantee, one can accelerate the training process of hashing without loss much of accuracy. With respect to the problem of large-scale multi-view clustering, the thesis contribute a novel method for graph-based clustering. A graph offers an attractive way of representing data and discovering the essential information such as the neighborhood structure. However, both of the graph construction process and graph-based learning techniques become computationally prohibitive at a large scale. To overcome these bottlenecks, we present a novel graph construction approach, called Salient Graphs, which enjoys linear space and time complexities and can thus be constructed over gigantic databases efficiently. Then, we implement an efficient graph-cut algorithm, which iteratively search consensus between multiple views and perform clustering. This results in an accurate and fast algorithm for multi-view data clustering. With respect to the problem of visual tracking, the thesis contribute a novel method for instrument tracking in retinal microsurgery. The instrument tracking is a key task in robot-assist surgical system. In this kind of system, data is collected and processing in real-time. Therefore, a tracking algorithm need to find good balance between accuracy and efficiency. The thesis proposed a novel visual tracker based on online learning. The proposed algorithm is able to run in video frame-rate while achieving the state-of-the-art accuracy.

Download or read book Recent Advances in Big Data Machine and Deep Learning for Precision Agriculture written by Muhammad Fazal Ijaz and published by Frontiers Media SA. This book was released on 2024-02-19 with total page 379 pages. Available in PDF, EPUB and Kindle. Book excerpt:

Download or read book Pattern Recognition and Computer Vision written by Jian-Huang Lai and published by Springer. This book was released on 2018-11-02 with total page 635 pages. Available in PDF, EPUB and Kindle. Book excerpt: The four-volume set LNCS 11256, 11257, 11258, and 11259 constitutes the refereed proceedings of the First Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2018, held in Guangzhou, China, in November 2018. The 179 revised full papers presented were carefully reviewed and selected from 399 submissions. The papers have been organized in the following topical sections: Part I: Biometrics, Computer Vision Application. Part II: Deep Learning. Part III: Document Analysis, Face Recognition and Analysis, Feature Extraction and Selection, Machine Learning. Part IV: Object Detection and Tracking, Performance Evaluation and Database, Remote Sensing.

Download or read book Metric Learning Applied for Automatic Large Scale Image Classification written by Sahilu Wendeson Sahilu and published by . This book was released on 2014 with total page pages. Available in PDF, EPUB and Kindle. Book excerpt: In the current Internet world, the numbers of digital images are growing exponentially. As a result, it is very tough to retrieve relevant objects for a given query point. For the past few years, researchers have been contributing different algorithms in the two most common machine learning categories to either cluster or classify images. There are several techniques of supervised classification images depending on the local or global feature representation of images, and on the metric used to calculate the distance (or similarity) between images. Recently many studies have shown the interest to learn a metric rather than use a simple metric a priori (e.g. Euclidean distance). This approach is described in the literature as metric learning. The main objective of this thesis is to use metric learning algorithm in the context of large-scale image classification. In this project, we use a metric learning algorithm which is driven by the nearest neighbors approach and has a competence to improve the generic k Nearest Neighbor (kNN) machine learning algorithm. Even though we get significant improvement on the performance of classification, the computation is very expensive due to the large dimensionality of our input dataset. Thus, we use the dimension reduction technique to reduce dimension and computation time as well. Nevertheless, due to the size of the database, classifying and searching a given query point using metric learning algorithm alone exhaustively is intractable.

Download or read book Deep Learning for Marine Science written by Haiyong Zheng and published by Frontiers Media SA. This book was released on 2024-05-15 with total page 555 pages. Available in PDF, EPUB and Kindle. Book excerpt: Deep learning (DL), mainly composed of deep and complex neural networks such as recurrent network and convolutional network, is an emerging research branch in the field of artificial intelligence and machine learning. DL revolution has a far-reaching impact on all scientific disciplines and every corner of our lives. With continuing technological advances, marine science is entering into the big data era with the exponential growth of information. DL is an effective means of harnessing the power of big data. Combined with unprecedented data from cameras, acoustic recorders, satellite remote sensing, and large model outputs, DL enables scientists to solve complex problems in biology, ecosystems, climate, energy, as well as physical and chemical interactions. Although DL has made great strides, it is still only beginning to emerge in many fields of marine science, especially towards representative applications and best practices for the automatic analysis of marine organisms and marine environments. DL in nowadays' marine science mainly leverages cutting-edge techniques of deep neural networks and massive data which collected by in-situ optical or acoustic imaging sensors for underwater applications, such as plankton classification and coral reef detection. This research topic aims to expand the applications of marine science to cover all aspects of detection, classification, segmentation, localization, and density estimation of marine objects, organisms, and phenomena.

Download or read book Deep Learning for Recognition of Objects Activities Faces and Spatio temporal Patterns written by Amir Ghaderi and published by . This book was released on 2019 with total page 63 pages. Available in PDF, EPUB and Kindle. Book excerpt: A popular method in machine learning is Convolutional Neural Network (CNN). CNN had was of high interest to the research community in the 1990s, but after that its popularity receded compared to the Support Vector Machine Support Vector Machine (SVM)[1]. One of the reasons was the relatively lower computational demands of SVM. Training CNNs requires significantly more computational power, time, and data than training SVM. One of the important issues in showing the power of the CNN is the availability of the huge amount of data and introducing big datasets. With increased availability of powerful GPU processing, using several improvements in network structure, and using much more data Krizhevsky et al. [2] used CNN to achieve the highest image classification accuracy on ImageNet Large Scale Visual Recognition Challenge(ILSVRC) [3]. After that result, CNNs have become widely popular in the computer vision and pattern recognition community, and have been applied to a variety of classification problems, including detection and localization. CNNs have achieved the best results for detection on the PASCAL VOC dataset [1], and for classification on the Caltech-256 [4] and Caltech-101 datasets [4, 5]. Based on such results, CNNs have emerged as a leading method for Machine learning and the term Deep Learning was emerged. The origin of deep learning is in computer vision. However, researchers found that deep learning is a very powerful tool to solve many problems in other areas like forecasting, finance, human pose estimation, Natural Language Processing (NLP), etc. Deep learning based methods showed a wonderful performance relate to other available methods. We have tried to improve deep learning methods and using them for solving problems in different areas. In this thesis, we will try to use the deep learning techniques for solving problems indifferent areas such as unsupervised learning, object classification, forecasting, cognitive behavior assessment and face recognition. In the computer vision part, a novel method for unsupervised feature learning for image classification was proposed in the thesis. Training CNN needs huge amount of data. So, finding the methods to train CNN with unlabeled data is very promising. In the second part, we proposed a new deep learning based framework for forecasting. Forecasting is a challenging task and has many applications in finance, meteorology, etc. We have proposed a new framework for forecasting in cases that there are many nodes to generate data. One application of our framework is prediction of the wind speed for multiple stations around the country. Another problem that we have been using Deep Learning (DL) to solve is face recognition at scale. Face recognition is very demanding both in academic and industry. We applied DL for solving face recognition for more than 600,000 identities. Also, we used DL to improve the performance of the system for behavioral assessment. This thesis makes the following contributions. First, we proposed a method for unsupervised feature learning for object classification. Due to need for huge amount of labeled data for training neural networks, unsupervised learning is very appealing for CNN training. Representation learning with unlabeled data is an interesting and open problem in machine learning community. We used transfer learning to transfer knowledge from trained network in a dataset to test samples from other dataset. The results are promising and we compare them to other methods. There are some ideas in this topic to improve the results which we implement them in the future. The paper was published at ICPR 2016. Second, we solved a forecasting problem with proposing a new deep learning based framework. We presented a spatio-temporal wind speed forecasting algorithm using DL and in particular, Recurrent Neural Networks (RNNs). we modeled the spatio-temporal information by a graph whose nodes are data generating entities and its edges basically model how these nodes are interacting with each other. Available methods for forecasting propose models to forecast wind speed for only one node. One of the main contributions of our work is the fact that we obtain forecasts of all nodes of the graph at the same time based on one framework. Our paper in this project was published at ICML Time Series workshop 2017. We improved the motion analysis module for HTKS assessment. HTKS [6] is a game-like cognitive assessment method, designed for children between four and eight years of age. During the HTKS assessment, a child responds to a sequence of requests, such as"touch your head" or "touch your toes". The cognitive challenge stems from the fact that the children are instructed to interpret these requests not literally, but by touching a different body part than the one stated. In prior work, we have developed the CogniLearn system, that captures data from subjects performing the HTKS game, and analyzes the motion of the subjects. We propose specific improvements that make the motion analysis module more accurate. As a result of these improvements, the accuracy in recognizing cases where subjects touch their toes has gone from 76.46% in our previous work to 97.19%. The paper was published at PETRA 2017. Finally, a method proposed for face recognition at scale for large number of identities. We used the triplet loss function to train the neural network for feature learning. In our problem for face recognition we have huge number of classes so we can not use soft maxin the last layer of the network like what is done for usual classification problems. So, we used the triplet loss function for the network to create features and then we used a classifier on top of the features. The triplet loss function tries to minimize the distance of samples in a class and maximize the distance of a class with other classes. As a result of CNN for representation learning, each image could be converted to a 128-dimensional vector. We have done experiments on different number of classes on different datasets like FLW, MegaFace, and Face Scrub. The number of classes are 500, 5K, 10K, 20K, 100K, and 663386.

Download or read book Computer Vision ECCV 2012 written by Andrew Fitzgibbon and published by Springer. This book was released on 2012-09-26 with total page 909 pages. Available in PDF, EPUB and Kindle. Book excerpt: The seven-volume set comprising LNCS volumes 7572-7578 constitutes the refereed proceedings of the 12th European Conference on Computer Vision, ECCV 2012, held in Florence, Italy, in October 2012. The 408 revised papers presented were carefully reviewed and selected from 1437 submissions. The papers are organized in topical sections on geometry, 2D and 3D shapes, 3D reconstruction, visual recognition and classification, visual features and image matching, visual monitoring: action and activities, models, optimisation, learning, visual tracking and image registration, photometry: lighting and colour, and image segmentation.

Download or read book Advances in Knowledge Discovery and Management written by Fabrice Guillet and published by Springer. This book was released on 2013-10-25 with total page 183 pages. Available in PDF, EPUB and Kindle. Book excerpt: This book is a collection of representative and novel works done in Data Mining, Knowledge Discovery, Clustering and Classification that were originally presented in French at the EGC'2012 Conference held in Bordeaux, France, on January 2012. This conference was the 12th edition of this event, which takes place each year and which is now successful and well-known in the French-speaking community. This community was structured in 2003 by the foundation of the French-speaking EGC society (EGC in French stands for ``Extraction et Gestion des Connaissances'' and means ``Knowledge Discovery and Management'', or KDM). This book is intended to be read by all researchers interested in these fields, including PhD or MSc students, and researchers from public or private laboratories. It concerns both theoretical and practical aspects of KDM. The book is structured in two parts called ``Knowledge Discovery and Data Mining'' and ``Classification and Feature Extraction or Selection''. The first part (6 chapters) deals with data clustering and data mining. The three remaining chapters of the second part are related to classification and feature extraction or feature selection.

Download or read book Image Processing in Agriculture and Forestry written by Gonzalo Pajares Martinsanz and published by MDPI. This book was released on 2018-09-27 with total page 223 pages. Available in PDF, EPUB and Kindle. Book excerpt: This book is a printed edition of the Special Issue "Image Processing in Agriculture and Forestry" that was published in J. Imaging

Download or read book Image Analysis and Processing ICIAP 2022 written by Stan Sclaroff and published by Springer Nature. This book was released on 2022-05-14 with total page 507 pages. Available in PDF, EPUB and Kindle. Book excerpt: The proceedings set LNCS 13231, 13232, and 13233 constitutes the refereed proceedings of the 21st International Conference on Image Analysis and Processing, ICIAP 2022, which was held during May 23-27, 2022, in Lecce, Italy, The 168 papers included in the proceedings were carefully reviewed and selected from 307 submissions. They deal with video analysis and understanding; pattern recognition and machine learning; deep learning; multi-view geometry and 3D computer vision; image analysis, detection and recognition; multimedia; biomedical and assistive technology; digital forensics and biometrics; image processing for cultural heritage; robot vision; etc.

Download or read book Engineering Applications of Neural Networks written by Lazaros Iliadis and published by Springer Nature. This book was released on 2023-06-06 with total page 636 pages. Available in PDF, EPUB and Kindle. Book excerpt: This book constitutes the refereed proceedings of the 24th International Conference on Engineering Applications of Neural Networks, EANN 2023, held in León, Spain, in June 2023. The 41 revised full papers and 8 revised short papers presented were carefully reviewed and selected from 125 submissions. The papers are organized in topical sections on ​artificial intelligence - computational methods - ethology; classification - filtering - genetic algorithms; complex dynamic networks' optimization/ graph neural networks; convolutional neural networks/spiking neural networks; deep learning modeling; deep/machine learning in engineering; LEARNING (reinforcemet - federated - adversarial - transfer); natural language - recommendation systems.

Download or read book Advanced Research and Applications of Deep Learning and Neural Network in Image Recognition written by Ganggang Dong and published by . This book was released on 2024-03-08 with total page 0 pages. Available in PDF, EPUB and Kindle. Book excerpt: This reprint aims to immerse the reader in the latest research and applications of deep learning and neural networks in image recognition. Deep learning algorithms are the major driving force behind recent advances in image classification. The success of deep learning is powered by two crucial issues: large-scale training datasets and powerful computational platforms. In most cases, the performances obtained by deep neural networks are much better than those of hand-crafted delicate image features. Yet, despite the great success of deep learning in image recognition, numerous challenges remain. This Special Issue aims to present new solutions to these challenging problems.

Download or read book Cognitive NeuroIntelligence written by Jia Liu and published by Frontiers Media SA. This book was released on 2021-09-23 with total page 172 pages. Available in PDF, EPUB and Kindle. Book excerpt:

Download or read book The Palgrave Handbook of Sustainable Digitalization for Business Industry and Society written by Myriam Ertz and published by Springer Nature. This book was released on with total page 444 pages. Available in PDF, EPUB and Kindle. Book excerpt:

Download or read book Artificial Intelligence and MRI Boosting Clinical Diagnosis written by Antonio Napolitano and published by Frontiers Media SA. This book was released on 2022-08-05 with total page 322 pages. Available in PDF, EPUB and Kindle. Book excerpt:

Download or read book Advances in Visual Computing written by George Bebis and published by Springer Nature. This book was released on 2020-12-11 with total page 763 pages. Available in PDF, EPUB and Kindle. Book excerpt: This two-volume set of LNCS 12509 and 12510 constitutes the refereed proceedings of the 15th International Symposium on Visual Computing, ISVC 2020, which was supposed to be held in San Diego, CA, USA in October 2020, took place virtually instead due to the COVID-19 pandemic. The 114 full and 4 short papers presented in these volumes were carefully reviewed and selected from 175 submissions. The papers are organized into the following topical sections: Part I: deep learning; segmentation; visualization; video analysis and event recognition; ST: computational bioimaging; applications; biometrics; motion and tracking; computer graphics; virtual reality; and ST: computer vision advances in geo-spatial applications and remote sensing Part II: object recognition/detection/categorization; 3D reconstruction; medical image analysis; vision for robotics; statistical pattern recognition; posters