The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
We present Deeply Supervised Object Detector (DSOD), a framework that can learn object detectors from scratch. State-of-the-art object objectors rely heavily on the off the-shelf networks pre-trained on large-scale classification datasets like Image Net, which incurs learning bias due to the difference on both the loss functions and the category distributions between classification and detection tasks...
We propose the Anchored Regression Network (ARN), a nonlinear regression network which can be seamlessly integrated into various networks or can be used stand-alone when the features have already been fixed. Our ARN is a smoothed relaxation of a piecewise linear regressor through the combination of multiple linear regressors over soft assignments to anchor points. When the anchor points are fixed...
We propose a novel framework for abnormal event detection in video that requires no training sequences. Our framework is based on unmasking, a technique previously used for authorship verification in text documents, which we adapt to our task. We iteratively train a binary classifier to distinguish between two consecutive video sequences while removing at each step the most discriminant features....
By analyzing the disadvantages of the traditional KNN using lazy learning that directly classify the data based on the K neighboring classes using the majority voting method, a new Sigmoid weighted classification algorithm WKS (Weighted KNN Based On Sigmoid) was proposed. WKS provides a new method for learning and training, since each training data di ∊ D contributes to the correct classification...
Training and testing unmanned vehicles need various real data. However, data of some special or dangerous testing environment may not be accessible, or may only be accessible at certain times. So, using generative adversarial networks to learn the real traffic scene and generate a new scene is an effective way of solving the problem. In this paper, a framework of deep convolutional generative adversarial...
Convolutional neural networks showed the ability in stereo matching cost learning. Recent approaches learned parameters from public datasets that have ground truth disparity maps. Due to the difficulty of labeling ground truth depth, usable data for system training is rather limited, making it difficult to apply the system to real applications. In this paper, we present a framework for learning stereo...
The success of deep learning in vision can be attributed to: (a) models with high capacity; (b) increased computational power; and (c) availability of large-scale labeled data. Since 2012, there have been significant advances in representation capabilities of the models and computational capabilities of GPUs. But the size of the biggest dataset has surprisingly remained constant. What will happen...
This paper presents a novel approach to launch and defend against the causative and evasion attacks on machine learning classifiers. As the preliminary step, the adversary starts with an exploratory attack based on deep learning (DL) and builds a functionally equivalent classifier by polling the online target classifier with input data and observing the returned labels. Using this inferred classifier,...
Many machine learning tasks have been shown solvable with impressive levels of success given large amounts of training data and computational power. For the problems which lack data sufficient to achieve high performance, methods for transfer learning can be applied. These refer to performing the new task while having prior knowledge of the nature of the data, gained by first performing a different...
Deep neural networks have been widely applied in the field of environmental sound classification. However, due to the scarcity of carefully labeled data, their training process suffers from over-fitting. Data augmentation is a technique that alleviates this issue. It augments the training set with synthetic data that are created by modifying some parameters of the real data. However, not all kinds...
Deep neural networks (DNN) have been successfully employed for the problem of monaural sound source separation achieving state-of-the-art results. In this paper, we propose using convolutional recurrent neural network (CRNN) architecture for tackling this problem. We focus on a scenario where low algorithmic delay (< 10 ms) is paramount, and relatively little training data is available. We show...
In this current age, numerous ranges of real word applications with imbalanced dataset is one of the foremost focal point of researcher's inattention. There is the enormous increment of data generation and imbalance within dataset. Processing and knowledge extraction of huge amount of imbalanced data becomes a challenge related with space and time necessities. Generally there is a list of an assortment...
Dropout is a technique widely used for preventing overfitting while training deep neural networks. However, applying dropout to a neural network typically increases the training time. This paper proposes a different dropout approach called controlled dropout that improves training speed by dropping units in a column-wise or row-wise manner on the matrices. In controlled dropout, a network is trained...
A hybrid sampling technique is proposed by combining Complementary Fuzzy Support Vector Machine (CMTFSVM) and Synthetic Minority Oversampling Technique (SMOTE) for handling the imbalanced classification problem. The proposed technique uses an optimised membership function to enhance the classification performance and it is compared with three different classifiers. The experiments consisted of four...
There has been a phenomenal increase in the utility of text classification (TC) in applications like targeted advertisement and sentiment analysis. Most applications demand that the model be efficient and robust, yet produce accurate categorizations. This is quite challenging as their is a dearth of labelled training data because it requires assigning labels after reading the whole document. Secondly,...
The enhancement of speech degraded with the non-stationary noise types that typify real-world conditions has remained a challenging problem for several decades. However, recent use of data driven methods for this task has brought great performance improvements. In this paper, we develop a speech enhancement framework based on the extreme learning machine. Experimental results show that the proposed...
This paper presents a novel approach for remaining useful life (RUL) prediction of rotating machinery using hierarchical deep neural networks (DNN). The different health stages are classified by a DNN-based health stage classifier trained by segmented degradation signal. This method builds several RUL predictors based on the health stages of the degradation process. Instead of modeling the entire...
Building language models for source code enables a large set of improvements on traditional software engineering tasks. One promising application is automatic code completion. State-of-the-art techniques capture code regularities at token level with lexical information. Such language models are more suitable for predicting short token sequences, but become less effective with respect to long statement...
With the proliferation of Android-based devices, malicious apps have increasingly found their way to user devices. Many solutions for Android malware detection rely on machine learning; although effective, these are vulnerable to attacks from adversaries who wish to subvert these algorithms and allow malicious apps to evade detection. In this work, we present a statistical analysis of the impact of...
We present a neural network model that learns to produce music scores directly from audio signals. Instead of employing commonplace processing steps, such as frequency transform front-ends, harmonicity and scale priors, or temporal pitch smoothing, we show that a neural network can learn such steps on its own when presented with the appropriate training data. We show how such a network can perform...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.