This will count as one of your downloads.
You will have access to both the presentation and article (if available).
When dealing with sparse or no labeled data in the target domain, transfer learning shows its appealing performance by borrowing the supervised knowledge from external domains. Recently deep structure learning has been exploited in transfer learning due to its attractive power in extracting effective knowledge through multi-layer strategy, so that deep transfer learning is promising to address the cross-domain mismatch. In general, cross-domain disparity can be resulted from the difference between source and target distributions or different modalities, e.g., Midwave IR (MWIR) and Longwave IR (LWIR). In this paper, we propose a Weighted Deep Transfer Learning framework for automatic target classification through a task-driven fashion. Specifically, deep features and classifier parameters are obtained simultaneously for optimal classification performance. In this way, the proposed deep structures can extract more effective features with the guidance of the classifier performance; on the other hand, the classifier performance is further improved since it is optimized on more discriminative features. Furthermore, we build a weighted scheme to couple source and target output by assigning pseudo labels to target data, therefore we can transfer knowledge from source (i.e., MWIR) to target (i.e., LWIR). Experimental results on real databases demonstrate the superiority of the proposed algorithm by comparing with others.
This will count as one of your downloads.
You will have access to both the presentation and article (if available).
This course provides a broad introduction to the basic concept of automatic target and object detection and its applications in Hyperspectral Imagery (HSI). The primary goal of this course is to introduce the well known target detection algorithms in hyperspectral imagery. Examples of the classical target detection techniques such as spectral matched filter, subspace matched filter, adaptive matched filter, orthogonal subspace, support vector machine (SVM) and machine learning are reviewed. Construction of invariance subspaces for target and background as well as the use of regularization techniques are presented. Standard atmospheric correction and compensation techniques are reviewed. Anomaly detection techniques for HSI and dual band FLIR imagery are also discussed. Applications of HSI for detection of mines, targets, humans, chemical plumes and anomalies are reviewed.
This course provides a broad introduction to the basic concept of the classical neural networks (NN) and its current evolution to deep learning (DL) technology. The primary goal of this course is to introduce the well-known deep learning architectures and their applications in defense and security for object detection, identification, verification, action recognition, scene understanding and biometrics using a single modality or multimodality sensor information. This course will describe the history of neural networks and its progress to current deep learning technology. It covers several DL architectures such the classical multi-layer feed forward neural networks, convolutional neural networks (CNN), restricted Boltzmann machines (RBM), auto-encoders and recurrent neural networks such as long term short memory (LSTM). Use of deep learning architectures for feature extraction and classification will be described and demonstrated. Examples of popular CNN-based architectures such as AlexNet, VGGNet, GooGleNet (inception modules), ResNet, DeepFace, Highway Networks, FractalNet and their applications to defense and security will be discussed. Advanced architectures such as Siamese deep networks, coupled neural networks, auto-encoders, fusion of multiple CNNs and their applications to object verification and classification will also be covered.
This course provides a broad introduction to the basic concept of the classical neural networks (NN) and its current evolution to deep learning (DL) technology. The primary goal of this course is to introduce the well-known deep learning architectures and their applications in image processing for object detection, identification, verification, action recognition, scene understanding and biometrics using a single modality or multimodality sensor information. This course will describe the history of neural networks and its progress to current deep learning technology. It covers several DL architectures such the classical multi-layer feed forward neural networks, convolutional neural networks (CNN), restricted Boltzmann machines (RBM), auto-encoders and recurrent neural networks such as long term short memory (LSTM). Use of deep learning architectures for feature extraction and classification will be described and demonstrated. <p> </p> Examples of popular CNN-based architectures such as AlexNet, VGGNet, GooGleNet (inception modules), ResNet, DeepFace, Highway Networks, FractalNet and their applications to defense and security will be discussed. Advanced architectures such as Siamese deep networks, coupled neural networks, auto-encoders, fusion of multiple CNNs and their applications to object verification and classification will also be covered.
This course provides a broad introduction to the basic concepts of artificial neural networks and its applications in image processing. A large number of neural network architectures and their training algorithms are reviewed. Examples of neural networks architectures that are covered in this course are single layer perceptrons, multilayer perceptrons, time-delay neural networks, Kohonen feature maps, learning vector quantization, radial basis function and Hopfield neural networks. An introduction to support vector machine and learning theory is provided. Applications that are covered are object and pattern recognition, object inspection, classifiers, handwritten word and digit recognition, automatic target recognition, and image compression.
This course introduces the basic concepts of using artificial neural networks for Automatic Target Recognition (ATR). Neural network-based ATR algorithms are reviewed. Sensors covered are forward-looking infrared (FLIR), synthetic aperture radar (SAR), laser radar, and high resolution sonar imagery. Neural network-based detection (cueing), clutter false alarm rejection, feature extraction, recognition, classification, segmentation and enhancement techniques are described. Clutter representation and characterization are discussed. Sensor fusion algorithms based on neural network techniques are also reviewed.
View contact details
No SPIE Account? Create one
