We tackle the problem of large scale visual place recognition, where the task is to quickly and accurately recognize the location of a given query photograph. We present the following four principal ...contributions. First, we develop a convolutional neural network (CNN) architecture that is trainable in an end-to-end manner directly for the place recognition task. The main component of this architecture, NetVLAD, is a new generalized VLAD layer, inspired by the "Vector of Locally Aggregated Descriptors" image representation commonly used in image retrieval. The layer is readily pluggable into any CNN architecture and amenable to training via backpropagation. Second, we create a new weakly supervised ranking loss, which enables end-to-end learning of the architecture's parameters from images depicting the same places over time downloaded from Google Street View Time Machine. Third, we develop an efficient training procedure which can be applied on very large-scale weakly labelled tasks. Finally, we show that the proposed architecture and training procedure significantly outperform non-learnt image representations and off-the-shelf CNN descriptors on challenging place recognition and image retrieval benchmarks.
We tackle the problem of large scale visual place recognition, where the task is to quickly and accurately recognize the location of a given query photograph. We present the following three principal ...contributions. First, we develop a convolutional neural network (CNN) architecture that is trainable in an end-to-end manner directly for the place recognition task. The main component of this architecture, NetVLAD, is a new generalized VLAD layer, inspired by the "Vector of Locally Aggregated Descriptors" image representation commonly used in image retrieval. The layer is readily pluggable into any CNN architecture and amenable to training via backpropagation. Second, we develop a training procedure, based on a new weakly supervised ranking loss, to learn parameters of the architecture in an end-to-end manner from images depicting the same places over time downloaded from Google Street View Time Machine. Finally, we show that the proposed architecture significantly outperforms non-learnt image representations and off-the-shelf CNN descriptors on two challenging place recognition benchmarks, and improves over current state of-the-art compact image representations on standard image retrieval benchmarks.
The aim of this work is to localize a query photograph by finding other images depicting the same place in a large geotagged image database. This is a challenging task due to changes in viewpoint, ...imaging conditions and the large size of the image database. The contribution of this work is two-fold. First, we cast the place recognition problem as a classification task and use the available geotags to train a classifier for each location in the database in a similar manner to per-exemplar SVMs in object recognition. Second, as only few positive training examples are available for each location, we propose a new approach to calibrate all the per-location SVM classifiers using only the negative examples. The calibration we propose relies on a significance measure essentially equivalent to the p-values classically used in statistical hypothesis testing. Experiments are performed on a database of 25,000 geotagged street view images of Pittsburgh and demonstrate improved place recognition accuracy of the proposed approach over the previous work.
The aim of this work is to localize a query photograph by finding other images depicting the same place in a large geotagged image database. This is a challenging task due to changes in viewpoint, ...imaging conditions and the large size of the image database. The contribution of this work is two-fold. First, we cast the place recognition problem as a classification task and use the available geotags to train a classifier for each location in the database in a similar manner to per-exemplar SVMs in object recognition. Second, as only one or a few positive training examples are available for each location, we propose two methods to calibrate all the per-location SVM classifiers without the need for additional positive training data. The first method relies on p-values from statistical hypothesis testing and uses only the available negative training data. The second method performs an affine calibration by appropriately normalizing the learnt classifier hyperplane and does not need any additional labelled training data. We test the proposed place recognition method with the bag-of-visual-words and Fisher vector image representations suitable for large scale indexing. Experiments are performed on three datasets: 25,000 and 55,000 geotagged street view images of Pittsburgh, and the 24/7 Tokyo benchmark containing 76,000 images with varying illumination conditions. The results show improved place recognition accuracy of the learnt image representation over direct matching of raw image descriptors.
We tackle the problem of large scale visual place recognition, where the task is to quickly and accurately recognize the location of a given query photograph. We present the following four principal ...contributions. First, we develop a convolutional neural network (CNN) architecture that is trainable in an end-to-end manner directly for the place recognition task. The main component of this architecture, NetVLAD, is a new generalized VLAD layer, inspired by the " Vector of Locally Aggregated Descriptors " image representation commonly used in image retrieval. The layer is readily pluggable into any CNN architecture and amenable to training via backpropagation. Second, we create a new weakly supervised ranking loss, which enables end-to-end learning of the architecture's parameters from images depicting the same places over time downloaded from Google Street View Time Machine. Third, we develop an efficient training procedure which can be applied on very large-scale weakly labelled tasks. Finally, we show that the proposed architecture and training procedure significantly outperform non-learnt image representations and off-the-shelf CNN descriptors on challenging place recognition and image retrieval benchmarks.
Advances in large language models have notably enhanced the efficiency of information extraction from unstructured and semi-structured data sources. As these technologies become integral to various ...applications, establishing an objective measure for the quality of information extraction becomes imperative. However, the scarcity of labeled data presents significant challenges to this endeavor. In this paper, we introduce an automatic framework to assess the quality of the information extraction/retrieval and its completeness. The framework focuses on information extraction in the form of entity and its properties. We discuss how to handle the input/output size limitations of the large language models and analyze their performance when extracting the information. In particular, we introduce scores to evaluate the quality of the extraction and provide an extensive discussion on how to interpret them.
This paper addresses the detection of malware activity in a running application on the Android system. The detection is based on dynamic analysis and is formulated as a weakly supervised problem. We ...design an RNN sequential architecture able to continuously detect malicious activity using the proposed max-loss objective. The experiments were performed on a large industrial dataset consisting of 361,265 samples. The results demonstrate the performance of 96.2% true positive rate at 1.6% false positive rate which is superior to the state-of-the-art results. As part of this work, we release the dataset to the public.
Place recognition is formulated as a task of finding the location where the query image was captured. This is an important task that has many practical applications in robotics, autonomous driving, ...augmented reality, 3D reconstruction or systems that organize imagery in geographically structured manner. Place recognition is typically done by finding a reference image in a large structured geo-referenced database.In this work, we first address the problem of building a geo-referenced dataset for place recognition. We describe a framework for building the dataset from the street-side imagery of the Google Street View that provides panoramic views from positions along many streets, cities and rural areas worldwide. Besides of downloading the panoramic views and ability to transform them into a set of perspective images, the framework is capable of getting underlying scene depth information.Second, we aim at localizing a query photograph by finding other images depicting the same place in a large geotagged image database. This is a challenging task due to changes in viewpoint, imaging conditions and the large size of the image database. The contribution of this work is two-fold; (i) we cast the place recognition problem as a classification task and use the available geotags to train a classifier for each location in the database in a similar manner to per-exemplar SVMs in object recognition, and (ii) as only a few positive training examples are available for each location, we propose two methods to calibrate all the per-location SVM classifiers without the need for additional positive training data. The first method relies on p-values from statistical hypothesis testing and uses only the available negative training data. The second method performs an affine calibration by appropriately normalizing the learned classifier hyperplane and does not need any additional labeled training data. We test the proposed place recognition method with the bag-of-visual-words and Fisher vector image representations suitable for large scale indexing.Experiments are performed on three datasets: 25,000 and 55,000 geotagged street view images of Pittsburgh, and the 24/7 Tokyo benchmark containing 76,000 images with varying illumination conditions. The results show improved place recognition accuracy of the learned image representation over direct matching of raw image descriptors.
碩士
中華大學
機械工程學系碩士班
97
In this work a mathematical model of a cylindrical bending of a plate on an elastic foun-
dation is presented. The possible application in MEMS pressure sensor part is discussed.
...The second part of this textbook is focused on selected theoretical details of precision
3D computer vision measurements and software design. A precision camera calibration
procedure is described and details of the easy calibration technique are given in text. A
new approach for fast normalized cross-correlation in Fourier domain is presented and a
novel approach for normalized cross-correlation method for color images is shown. Clear
and detailed description of a digital image correlation using the Newton-Raphson method
is presented along with a detailed description of the algorithm. The experimental setup
for single-camera and two-camera measurements is explained. Finally, the method and
functionality of designed software are demonstrated on two experiments and results are
discussed. Possible applications and perspective research are suggested in the end of this
publication.
We tackle the problem of large scale visual place recognition, where the task is to quickly and accurately recognize the location of a given query photograph. We present the following three principal ...contributions. First, we develop a convolutional neural network (CNN) architecture that is trainable in an end-to-end manner directly for the place recognition task. The main component of this architecture, NetVLAD, is a new generalized VLAD layer, inspired by the "Vector of Locally Aggregated Descriptors" image representation commonly used in image retrieval. The layer is readily pluggable into any CNN architecture and amenable to training via backpropagation. Second, we develop a training procedure, based on a new weakly supervised ranking loss, to learn parameters of the architecture in an end-to-end manner from images depicting the same places over time downloaded from Google Street View Time Machine. Finally, we show that the proposed architecture significantly outperforms non-learnt image representations and off-the-shelf CNN descriptors on two challenging place recognition benchmarks, and improves over current state-of-the-art compact image representations on standard image retrieval benchmarks.