Quantitative Analysis of Image Classification Techniques for Memory-Constrained Devices

• URL: http://arxiv.org/abs/2005.04968v4
• Date: Sun, 15 Nov 2020 15:36:42 GMT
• Title: Quantitative Analysis of Image Classification Techniques for Memory-Constrained Devices
• Authors: Sebastian M\"uksch, Theo Olausson, John Wilhelm, Pavlos Andreadis
• Abstract summary: Convolutional Neural Networks, or CNNs, are the state of the art for image classification, but typically come at the cost of a large memory footprint. In this paper, we compare CNNs with ProtoNN, Bonsai and FastGRNN when applied to 3-channel image classification using CIFAR-10. We show that Direct Convolution CNNs perform best for all chosen budgets, with a top performance of 65.7% accuracy at a memory footprint of 58.23KB.
• Score: 0.7373617024876725
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Convolutional Neural Networks, or CNNs, are the state of the art for image classification, but typically come at the cost of a large memory footprint. This limits their usefulness in applications relying on embedded devices, where memory is often a scarce resource. Recently, there has been significant progress in the field of image classification on such memory-constrained devices, with novel contributions like the ProtoNN, Bonsai and FastGRNN algorithms. These have been shown to reach up to 98.2% accuracy on optical character recognition using MNIST-10, with a memory footprint as little as 6KB. However, their potential on more complex multi-class and multi-channel image classification has yet to be determined. In this paper, we compare CNNs with ProtoNN, Bonsai and FastGRNN when applied to 3-channel image classification using CIFAR-10. For our analysis, we use the existing Direct Convolution algorithm to implement the CNNs memory-optimally and propose new methods of adjusting the FastGRNN model to work with multi-channel images. We extend the evaluation of each algorithm to a memory size budget of 8KB, 16KB, 32KB, 64KB and 128KB to show quantitatively that Direct Convolution CNNs perform best for all chosen budgets, with a top performance of 65.7% accuracy at a memory footprint of 58.23KB.

Related papers

• Recurrent Neural Networks for Still Images [0.0]
  We argue that RNNs can effectively handle still images by interpreting the pixels as a sequence. We introduce a novel RNN design tailored for two-dimensional inputs, such as images, and a custom version of BiDirectional RNN (BiRNN) that is more memory-efficient than traditional implementations.
  arXiv  Detail & Related papers  (2024-09-10T06:07:20Z)
• Designing Extremely Memory-Efficient CNNs for On-device Vision Tasks [2.9835839258066015]
  We introduce a memory-efficient CNN (convolutional neural network) for on-device vision tasks. The proposed network classifies ImageNet with extremely low memory (i.e., 63 KB) while achieving competitive top-1 accuracy (i.e., 61.58%) To the best of our knowledge, the memory usage of the proposed network is far smaller than state-of-the-art memory-efficient networks.
  arXiv  Detail & Related papers  (2024-08-07T10:04:04Z)
• A Methodology for Improving Accuracy of Embedded Spiking Neural Networks through Kernel Size Scaling [6.006032394972252]
  Spiking Neural Networks (SNNs) can offer ultra low power/ energy consumption for machine learning-based applications. Currently, most of the SNN architectures need a significantly larger model size to achieve higher accuracy. We propose a novel methodology that improves the accuracy of SNNs through kernel size scaling.
  arXiv  Detail & Related papers  (2024-04-02T06:42:14Z)
• Sub-bit Neural Networks: Learning to Compress and Accelerate Binary Neural Networks [72.81092567651395]
  Sub-bit Neural Networks (SNNs) are a new type of binary quantization design tailored to compress and accelerate BNNs. SNNs are trained with a kernel-aware optimization framework, which exploits binary quantization in the fine-grained convolutional kernel space. Experiments on visual recognition benchmarks and the hardware deployment on FPGA validate the great potentials of SNNs.
  arXiv  Detail & Related papers  (2021-10-18T11:30:29Z)
• Greedy Network Enlarging [53.319011626986004]
  We propose a greedy network enlarging method based on the reallocation of computations. With step-by-step modifying the computations on different stages, the enlarged network will be equipped with optimal allocation and utilization of MACs. With application of our method on GhostNet, we achieve state-of-the-art 80.9% and 84.3% ImageNet top-1 accuracies.
  arXiv  Detail & Related papers  (2021-07-31T08:36:30Z)
• Quantized Neural Networks via {-1, +1} Encoding Decomposition and Acceleration [83.84684675841167]
  We propose a novel encoding scheme using -1, +1 to decompose quantized neural networks (QNNs) into multi-branch binary networks. We validate the effectiveness of our method on large-scale image classification, object detection, and semantic segmentation tasks.
  arXiv  Detail & Related papers  (2021-06-18T03:11:15Z)
• ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training [68.63354877166756]
  ActNN is a memory-efficient training framework that stores randomly quantized activations for back propagation. ActNN reduces the memory footprint of the activation by 12x, and it enables training with a 6.6x to 14x larger batch size.
  arXiv  Detail & Related papers  (2021-04-29T05:50:54Z)
• CNNs for JPEGs: A Study in Computational Cost [49.97673761305336]
  Convolutional neural networks (CNNs) have achieved astonishing advances over the past decade. CNNs are capable of learning robust representations of the data directly from the RGB pixels. Deep learning methods capable of learning directly from the compressed domain have been gaining attention in recent years.
  arXiv  Detail & Related papers  (2020-12-26T15:00:10Z)
• Resource-efficient DNNs for Keyword Spotting using Neural Architecture Search and Quantization [23.850887499271842]
  This paper introduces neural architecture search (NAS) for the automatic discovery of small models for keyword spotting. We employ a differentiable NAS approach to optimize the structure of convolutional neural networks (CNNs) to maximize the classification accuracy. Using NAS only, we were able to obtain a highly efficient model with 95.4% accuracy on the Google speech commands dataset.
  arXiv  Detail & Related papers  (2020-12-18T09:53:55Z)
• Leveraging Automated Mixed-Low-Precision Quantization for tiny edge microcontrollers [76.30674794049293]
  This paper presents an automated mixed-precision quantization flow based on the HAQ framework but tailored for the memory and computational characteristics of MCU devices. Specifically, a Reinforcement Learning agent searches for the best uniform quantization levels, among 2, 4, 8 bits, of individual weight and activation tensors. Given an MCU-class memory bound to 2MB for weight-only quantization, the compressed models produced by the mixed-precision engine result as accurate as the state-of-the-art solutions.
  arXiv  Detail & Related papers  (2020-08-12T06:09:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.