Paper Group ANR 1780
LBVCNN: Local Binary Volume Convolutional Neural Network for Facial Expression Recognition from Image Sequences. AX-DBN: An Approximate Computing Framework for the Design of Low-Power Discriminative Deep Belief Networks. Detection and Identification of Objects and Humans in Thermal Images. Active Transfer Learning Network: A Unified Deep Joint Spec …
LBVCNN: Local Binary Volume Convolutional Neural Network for Facial Expression Recognition from Image Sequences
| Title | LBVCNN: Local Binary Volume Convolutional Neural Network for Facial Expression Recognition from Image Sequences |
| Authors | Sudhakar Kumawat, Manisha Verma, Shanmuganathan Raman |
| Abstract | Recognizing facial expressions is one of the central problems in computer vision. Temporal image sequences have useful spatio-temporal features for recognizing expressions. In this paper, we propose a new 3D Convolution Neural Network (CNN) that can be trained end-to-end for facial expression recognition on temporal image sequences without using facial landmarks. More specifically, a novel 3D convolutional layer that we call Local Binary Volume (LBV) layer is proposed. The LBV layer, when used with our newly proposed LBVCNN network, achieve comparable results compared to state-of-the-art landmark-based or without landmark-based models on image sequences from CK+, Oulu-CASIA, and UNBC McMaster shoulder pain datasets. Furthermore, our LBV layer reduces the number of trainable parameters by a significant amount when compared to a conventional 3D convolutional layer. As a matter of fact, when compared to a 3x3x3 conventional 3D convolutional layer, the LBV layer uses 27 times less trainable parameters. |
| Tasks | Facial Expression Recognition |
| Published | 2019-04-16 |
| URL | http://arxiv.org/abs/1904.07647v1 |
| http://arxiv.org/pdf/1904.07647v1.pdf | |
| PWC | https://paperswithcode.com/paper/lbvcnn-local-binary-volume-convolutional |
| Repo | |
| Framework | |
AX-DBN: An Approximate Computing Framework for the Design of Low-Power Discriminative Deep Belief Networks
| Title | AX-DBN: An Approximate Computing Framework for the Design of Low-Power Discriminative Deep Belief Networks |
| Authors | Ian Colbert, Ken Kreutz-Delgado, Srinjoy Das |
| Abstract | The power budget for embedded hardware implementations of Deep Learning algorithms can be extremely tight. To address implementation challenges in such domains, new design paradigms, like Approximate Computing, have drawn significant attention. Approximate Computing exploits the innate error-resilience of Deep Learning algorithms, a property that makes them amenable for deployment on low-power computing platforms. This paper describes an Approximate Computing design methodology, AX-DBN, for an architecture belonging to the class of stochastic Deep Learning algorithms known as Deep Belief Networks (DBNs). Specifically, we consider procedures for efficiently implementing the Discriminative Deep Belief Network (DDBN), a stochastic neural network which is used for classification tasks, extending Approximation Computing from the analysis of deterministic to stochastic neural networks. For the purpose of optimizing the DDBN for hardware implementations, we explore the use of: (a)Limited precision of neurons and functional approximations of activation functions; (b) Criticality analysis to identify nodes in the network which can operate at reduced precision while allowing the network to maintain target accuracy levels; and (c) A greedy search methodology with incremental retraining to determine the optimal reduction in precision for all neurons to maximize power savings. Using the AX-DBN methodology proposed in this paper, we present experimental results across several network architectures that show significant power savings under a user-specified accuracy loss constraint with respect to ideal full precision implementations. |
| Tasks | |
| Published | 2019-03-11 |
| URL | http://arxiv.org/abs/1903.04659v2 |
| http://arxiv.org/pdf/1903.04659v2.pdf | |
| PWC | https://paperswithcode.com/paper/ax-dbn-an-approximate-computing-framework-for |
| Repo | |
| Framework | |
Detection and Identification of Objects and Humans in Thermal Images
| Title | Detection and Identification of Objects and Humans in Thermal Images |
| Authors | Manish Bhattarai, Manel Martínez-Ramón |
| Abstract | Intelligent detecting processing capabilities can be instrumental to improving safety and efficiency for firefighters and victims during firefighting activities. The objective of this research, is to create an automated system that is capable of real-time object detection and recognition that improves the situational awareness of firefighters on the scene. We have explored state of the art Machine Learning (ML) techniques to achieve this objective. The goal for this work is to maximize the situational awareness for fire-fighters by effectively exploiting the information gathered from the infrared camera and use a trained deep Convolutional Neural Network (CNN) system to classify and identify objects of interest in real time. In the midst of such critical circumstances created by a fire, this system is able to accurately inform the decision making process of firefighters in real time by extracting crucial information for processing. It is then able to make inferences about these circumstances to aid firefighters in safely navigating such hazardous and catastrophic environments. |
| Tasks | Decision Making, Object Detection, Real-Time Object Detection |
| Published | 2019-10-08 |
| URL | https://arxiv.org/abs/1910.03617v1 |
| https://arxiv.org/pdf/1910.03617v1.pdf | |
| PWC | https://paperswithcode.com/paper/detection-and-identification-of-objects-and |
| Repo | |
| Framework | |
Active Transfer Learning Network: A Unified Deep Joint Spectral-Spatial Feature Learning Model For Hyperspectral Image Classification
| Title | Active Transfer Learning Network: A Unified Deep Joint Spectral-Spatial Feature Learning Model For Hyperspectral Image Classification |
| Authors | Cheng Deng, Yumeng Xue, Xianglong Liu, Chao Li, Dacheng Tao |
| Abstract | Deep learning has recently attracted significant attention in the field of hyperspectral images (HSIs) classification. However, the construction of an efficient deep neural network (DNN) mostly relies on a large number of labeled samples being available. To address this problem, this paper proposes a unified deep network, combined with active transfer learning that can be well-trained for HSIs classification using only minimally labeled training data. More specifically, deep joint spectral-spatial feature is first extracted through hierarchical stacked sparse autoencoder (SSAE) networks. Active transfer learning is then exploited to transfer the pre-trained SSAE network and the limited training samples from the source domain to the target domain, where the SSAE network is subsequently fine-tuned using the limited labeled samples selected from both source and target domain by corresponding active learning strategies. The advantages of our proposed method are threefold: 1) the network can be effectively trained using only limited labeled samples with the help of novel active learning strategies; 2) the network is flexible and scalable enough to function across various transfer situations, including cross-dataset and intra-image; 3) the learned deep joint spectral-spatial feature representation is more generic and robust than many joint spectral-spatial feature representation. Extensive comparative evaluations demonstrate that our proposed method significantly outperforms many state-of-the-art approaches, including both traditional and deep network-based methods, on three popular datasets. |
| Tasks | Active Learning, Hyperspectral Image Classification, Image Classification, Transfer Learning |
| Published | 2019-04-04 |
| URL | http://arxiv.org/abs/1904.02454v1 |
| http://arxiv.org/pdf/1904.02454v1.pdf | |
| PWC | https://paperswithcode.com/paper/active-transfer-learning-network-a-unified |
| Repo | |
| Framework | |
