اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدPUNCH: Positive UNlabelled Classification based information retrieval in Hyperspectral images
70
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Hyperspectral images of land-cover captured by airborne or satellite-mounted sensors provide a rich source of information about the chemical composition of the materials present in a given place. This makes hyperspectral imaging an important tool for earth sciences, land-cover studies, and military and strategic applications. However, the scarcity of labeled training examples and spatial variability of spectral signature are two of the biggest challenges faced by hyperspectral image classification. In order to address these issues, we aim to develop a framework for material-agnostic information retrieval in hyperspectral images based on Positive-Unlabelled (PU) classification. Given a hyperspectral scene, the user labels some positive samples of a material he/she is looking for and our goal is to retrieve all the remaining instances of the query material in the scene. Additionally, we require the system to work equally well for any material in any scene without the user having to disclose the identity of the query material. This material-agnostic nature of the framework provides it with superior generalization abilities. We explore two alternative approaches to solve the hyperspectral image classification problem within this framework. The first approach is an adaptation of non-negative risk estimation based PU learning for hyperspectral data. The second approach is based on one-versus-all positive-negative classification where the negative class is approximately sampled using a novel spectral-spatial retrieval model. We propose two annotator models - uniform and blob - that represent the labelling patterns of a human annotator. We compare the performances of the proposed algorithms for each annotator model on three benchmark hyperspectral image datasets - Indian Pines, Pavia University and Salinas.
قيم البحث
اقرأ أيضاً
This report describes metrics for the evaluation of the effectiveness of segment-based retrieval based on existing binary information retrieval metrics. This metrics are described in the context of a task for the hyperlinking of video segments. This
evaluation approach re-uses existing evaluation measures from the standard Cranfield evaluation paradigm. Our adaptation approach can in principle be used with any kind of effectiveness measure that uses binary relevance, and for other segment-baed retrieval tasks. In our video hyperlinking setting, we use precision at a cut-off rank n and mean average precision.
The main contribution of this paper is to design an Information Retrieval (IR) technique based on Algorithmic Information Theory (using the Normalized Compression Distance- NCD), statistical techniques (outliers), and novel organization of data base
structure. The paper shows how they can be integrated to retrieve information from generic databases using long (text-based) queries. Two important problems are analyzed in the paper. On the one hand, how to detect false positives when the distance among the documents is very low and there is actual similarity. On the other hand, we propose a way to structure a document database which similarities distance estimation depends on the length of the selected text. Finally, the experimental evaluations that have been carried out to study previous problems are shown.
Hyperspectral image (HSI) classification has been widely adopted in applications involving remote sensing imagery analysis which require high classification accuracy and real-time processing speed. Methods based on Convolutional neural networks (CNNs
) have been proven to achieve state-of-the-art accuracy in classifying HSIs. However, CNN models are often too computationally intensive to achieve real-time response due to the high dimensional nature of HSI, compared to traditional methods such as Support Vector Machines (SVMs). Besides, previous CNN models used in HSI are not specially designed for efficient implementation on embedded devices such as FPGAs. This paper proposes a novel CNN-based algorithm for HSI classification which takes into account hardware efficiency. A customized architecture which enables the proposed algorithm to be mapped effectively onto FPGA resources is then proposed to support real-time on-board classification with low power consumption. Implementation results show that our proposed accelerator on a Xilinx Zynq 706 FPGA board achieves more than 70x faster than an Intel 8-core Xeon CPU and 3x faster than an NVIDIA GeForce 1080 GPU. Compared to previous SVM-based FPGA accelerators, we achieve comparable processing speed but provide a much higher classification accuracy.
Automatic language processing tools typically assign to terms so-called weights corresponding to the contribution of terms to information content. Traditionally, term weights are computed from lexical statistics, e.g., term frequencies. We propose a
new type of term weight that is computed from part of speech (POS) n-gram statistics. The proposed POS-based term weight represents how informative a term is in general, based on the POS contexts in which it generally occurs in language. We suggest five different computations of POS-based term weights by extending existing statistical approximations of term information measures. We apply these POS-based term weights to information retrieval, by integrating them into the model that matches documents to queries. Experiments with two TREC collections and 300 queries, using TF-IDF & BM25 as baselines, show that integrating our POS-based term weights to retrieval always leads to gains (up to +33.7% from the baseline). Additional experiments with a different retrieval model as baseline (Language Model with Dirichlet priors smoothing) and our best performing POS-based term weight, show retrieval gains always and consistently across the whole smoothing range of the baseline.
PDM Systems contain and manage heavy amount of data but the search mechanism of most of the systems is not intelligent which can process users natural language based queries to extract desired information. Currently available search mechanisms in alm
ost all of the PDM systems are not very efficient and based on old ways of searching information by entering the relevant information to the respective fields of search forms to find out some specific information from attached repositories. Targeting this issue, a thorough research was conducted in fields of PDM Systems and Language Technology. Concerning the PDM System, conducted research provides the information about PDM and PDM Systems in detail. Concerning the field of Language Technology, helps in implementing a search mechanism for PDM Systems to search users needed information by analyzing users natural language based requests. The accomplished goal of this research was to support the field of PDM with a new proposition of a conceptual model for the implementation of natural language based search. The proposed conceptual model is successfully designed and partially implementation in the form of a prototype. Describing the proposition in detail the main concept, implementation designs and developed prototype of proposed approach is discussed in this paper. Implemented prototype is compared with respective functions of existing PDM systems .i.e., Windchill and CIM to evaluate its effectiveness against targeted challenges.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
