An official website of the United States government
Deep convolutional neural networks (CNNs) have been successful in many tasks in machine vision, however, millions of weights in the form of thousands of convolutional filters in CNNs make them difficult for human interpretation or understanding in science. In this article, we introduce a greedy structural compression scheme to obtain smaller and more interpretable CNNs, while achieving close to original accuracy. The compression is based on pruning filters with the least contribution to the classification accuracy or the lowest Classification Accuracy Reduction (CAR) importance index. We demonstrate the interpretability of CAR-compressed CNNs by showing that our algorithm prunes filters with visually redundant functionalities such as color filters. These compressed networks are easier to interpret because they retain the filter diversity of uncompressed networks with an order of magnitude fewer filters. Finally, a variant of CAR is introduced to quantify the importance of each image category to each CNN filter. Specifically, the most and the least important class labels are shown to be meaningful interpretations of each filter.
more »
« less
ICNN: An iterative implementation of convolutional neural networks to enable energy and computational complexity aware dynamic approximation
With Convolutional Neural Networks (CNN) becoming more of a commodity in the computer vision field, many have attempted to improve CNN in a bid to achieve better accuracy to a point that CNN accuracies have surpassed that of human's capabilities. However, with deeper networks, the number of computations and consequently the power needed per classification has grown considerably. In this paper, we propose Iterative CNN (ICNN) by reformulating the CNN from a single feed-forward network to a series of sequentially executed smaller networks. Each smaller network processes a sub-sample of input image, and features extracted from previous network, and enhances the classification accuracy. Upon reaching an acceptable classification confidence, ICNN immediately terminates. The proposed network architecture allows the CNN function to be dynamically approximated by creating the possibility of early termination and performing the classification with far fewer operations compared to a conventional CNN. Our results show that this iterative approach competes with the original larger networks in terms of accuracy while incurring far less computational complexity by detecting many images in early iterations.
more »
« less
- PAR ID:
- 10076458
- Date Published:
- Journal Name:
- 2018 Design, Automation & Test in Europe Conference & Exhibition (DATE)
- Page Range / eLocation ID:
- 551 to 556
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Agaian, Sos S.; Jassim, Sabah A.; DelMarco, Stephen P.; Asari, Vijayan K. (Ed.)Neural networks have emerged to be the most appropriate method for tackling the classification problem for hyperspectral images (HIS). Convolutional neural networks (CNNs), being the current state-of-art for various classification tasks, have some limitations in the context of HSI. These CNN models are very susceptible to overfitting because of 1) lack of availability of training samples, 2) large number of parameters to fine-tune. Furthermore, the learning rates used by CNN must be small to avoid vanishing gradients, and thus the gradient descent takes small steps to converge and slows down the model runtime. To overcome these drawbacks, a novel quaternion based hyperspectral image classification network (QHIC Net) is proposed in this paper. The QHIC Net can model both the local dependencies between the spectral channels of a single-pixel and the global structural relationship describing the edges or shapes formed by a group of pixels, making it suitable for HSI datasets that are small and diverse. Experimental results on three HSI datasets demonstrate that the QHIC Net performs on par with the traditional CNN based methods for HSI Classification with a far fewer number of parameters. Keywords: Classification, deep learning, hyperspectral imaging, spectral-spatial feature learningmore » « less
-
null (Ed.)Abstract The method of neural networks (aka deep learning) has opened up many new opportunities to utilize remotely sensed images in meteorology. Common applications include image classification, e.g., to determine whether an image contains a tropical cyclone, and image-to-image translation, e.g., to emulate radar imagery for satellites that only have passive channels. However, there are yet many open questions regarding the use of neural networks for working with meteorological images, such as best practices for evaluation, tuning, and interpretation. This article highlights several strategies and practical considerations for neural network development that have not yet received much attention in the meteorological community, such as the concept of receptive fields, underutilized meteorological performance measures, and methods for neural network interpretation, such as synthetic experiments and layer-wise relevance propagation. We also consider the process of neural network interpretation as a whole, recognizing it as an iterative meteorologist-driven discovery process that builds on experimental design and hypothesis generation and testing. Finally, while most work on neural network interpretation in meteorology has so far focused on networks for image classification tasks, we expand the focus to also include networks for image-to-image translation.more » « less
-
In this paper, we show that hidden layer activations in overparameterized neural networks for image classification exist primarily in subspaces smaller than the actual model width. We further show that these subspaces can be identified early in training. Based on these observations, we show how to efficiently find small networks that exhibit similar accuracy to their overparameterized counterparts after only a few training epochs. We term these network architectures Principal Component Networks (PCNs). We evaluate PCNs on CIFAR-10 and ImageNet for VGG and ResNet style architectures and find that PCNs consistently reduce parameter counts with little accuracy loss, thus providing the potential to reduce the compu- tational costs of deep neural network training.more » « less
-
Zelinski, Michael E.; Taha, Tarek M.; Howe, Jonathan (Ed.)Image classification forms an important class of problems in machine learning and is widely used in many realworld applications, such as medicine, ecology, astronomy, and defense. Convolutional neural networks (CNNs) are machine learning techniques designed for inputs with grid structures, e.g., images, whose features are spatially correlated. As such, CNNs have been demonstrated to be highly effective approaches for many image classification problems and have consistently outperformed other approaches in many image classification and object detection competitions. A particular challenge involved in using machine learning for classifying images is measurement data loss in the form of missing pixels, which occurs in settings where scene occlusions are present or where the photodetectors in the imaging system are partially damaged. In such cases, the performance of CNN models tends to deteriorate or becomes unreliable even when the perturbations to the input image are small. In this work, we investigate techniques for improving the performance of CNN models for image classification with missing data. In particular, we explore training on a variety of data alterations that mimic data loss for producing more robust classifiers. By optimizing the categorical cross-entropy loss function, we demonstrate through numerical experiments on the MNIST dataset that training with these synthetic alterations can enhance the classification accuracy of our CNN models.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.23919/DATE.2018.8342068
