TL;DR
This paper introduces a bipolar morphological ResNet (BM-ResNet) that reduces computational complexity and hardware requirements for image classification, with minimal accuracy loss on MNIST and CIFAR-10 datasets.
Contribution
The paper presents a novel BM-ResNet architecture that replaces standard layers with bipolar morphological ones, significantly decreasing hardware needs while maintaining high accuracy.
Findings
2.1-2.9 times fewer logic gates required
15-30% lower latency
Minimal accuracy decrease from 99.3% to 99.1% on MNIST
Abstract
One of the most computationally intensive parts in modern recognition systems is an inference of deep neural networks that are used for image classification, segmentation, enhancement, and recognition. The growing popularity of edge computing makes us look for ways to reduce its time for mobile and embedded devices. One way to decrease the neural network inference time is to modify a neuron model to make it moreefficient for computations on a specific device. The example ofsuch a model is a bipolar morphological neuron model. The bipolar morphological neuron is based on the idea of replacing multiplication with addition and maximum operations. This model has been demonstrated for simple image classification with LeNet-like architectures [1]. In the paper, we introduce a bipolar morphological ResNet (BM-ResNet) model obtained from a much more complex ResNet architecture by converting its…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
Methods1x1 Convolution · Kaiming Initialization · Average Pooling · Global Average Pooling · Batch Normalization · *Communicated@Fast*How Do I Communicate to Expedia? · Residual Connection · Max Pooling · Residual Block · Convolution
