paper-with-me

Papers

Wavelet Feature Maps Compression for Low Bandwidth Convolutional Neural Networks

2021-09-29 · Yair Zohav, Shahaf E Finder, Maor Ashkenazi, Eran Treister

Quantization is one of the most effective techniques for compressing Convolutional Neural Networks (CNNs), which are known for requiring extensive computational resources. However, aggressive quantization may cause severe degradation in the prediction accuracy of such networks, especially in image-to-image tasks such as semantic segmentation and depth prediction. In this paper, we propose Wavelet Compressed Convolution (WCC)---a novel approach for activation maps compression for $1\times1$ convolutions (the workhorse of modern CNNs). WCC achieves compression ratios and computational savings that are equivalent to low bit quantization rates at a relatively minimal loss of accuracy. To this end, we use a hardware-friendly Haar-wavelet transform, known for its effectiveness in image compression, and define the convolution on the compressed activation map. WCC can be utilized with any $1\times1$ convolution in an existing network architecture. By combining WCC with light quantization, we show that we achieve compression rates equal to 2-bit and 1-bit with minimal degradation in image-to-image tasks.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Depth EstimationDepth PredictionImage CompressionQuantizationSemantic Segmentation

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Haar Wavelet Feature Compression for Quantized Graph Convolutional Networks

2021-10-10 · Moshe Eliasof, Benjamin Bodner, Eran Treister

Graph Convolutional Networks (GCNs) are widely used in a variety of applications, and can be seen as an unstructured version of standard Convolutional Neural Networks (CNNs). As in CNNs, the computational cost of GCNs fo…

Feature CompressionNode ClassificationPoint Cloud ClassificationQuantization+1

Wavelet Feature Maps Compression for Image-to-Image CNNs

2022-05-24 · Shahaf E. Finder, Yair Zohav, Maor Ashkenazi, Eran Treister

Convolutional Neural Networks (CNNs) are known for requiring extensive computational resources, and quantization is among the best and most common methods for compressing them. While aggressive quantization (i.e., less t…

Depth EstimationNeural Network CompressionQuantizationSemantic Segmentation

CAT: Compression-Aware Training for bandwidth reduction

2019-09-25 · Chaim Baskin, Brian Chmiel, Evgenii Zheltonozhskii, Ron Banner 외

Convolutional neural networks (CNNs) have become the dominant neural network architecture for solving visual processing tasks. One of the major obstacles hindering the ubiquitous use of CNNs for inference is their relati…

Quantization

Efficient Bearing Sensor Data Compression via an Asymmetrical Autoencoder with a Lifting Wavelet Transform Layer

2025-01-20 · Xin Zhu, Ahmet Enis Cetin

Bearing data compression is vital to manage the large volumes of data generated during condition monitoring. In this paper, a novel asymmetrical autoencoder with a lifting wavelet transform (LWT) layer is developed to co…

Data CompressionDecoderDenoising

Extended Bit-Plane Compression for Convolutional Neural Network Accelerators

2018-10-01 · Lukas Cavigelli, Luca Benini

After the tremendous success of convolutional neural networks in image classification, object detection, speech recognition, etc., there is now rising demand for deployment of these compute-intensive ML models on tightly…

image-classificationImage Classificationobject-detectionObject Detection+2