Recurrent Convolutions: A Model Compression Point of View
Recurrent convolution (RC) shares the same convolutional kernels and unrolls them multiple times, which is originally proposed to model time-space signals. We suggest that RC can be viewed as a model compression strategy for deep convolutional neural networks. RC reduces the redundancy across layers and is complementary to most existing model compression approaches. However, the performance of an RC network can't match the performance of its corresponding standard one, i.e. with the same depth but independent convolutional kernels. This reduces the value of RC for model compression. In this paper, we propose a simple variant which improves RC networks: The batch normalization layers of an RC module are learned independently (not shared) for different unrolling steps. We provide insights on why this works. Experiments on CIFAR show that unrolling a convolutional layer several steps can improve the performance, thus indirectly plays a role in model compression.
Code (0)
등록된 구현이 없습니다.
Tasks
Model CompressionRolling Shutter CorrectionSimilar Papers 제목 키워드 기반
3D Point Cloud Compression with Recurrent Neural Network and Image Compression Methods
Storing and transmitting LiDAR point cloud data is essential for many AV applications, such as training data collection, remote control, cloud services or SLAM. However, due to the sparsity and unordered structure of the…
Data CompressionImage CompressionPCAC-GAN: A Sparse-Tensor-Based Generative Adversarial Network for 3D Point Cloud Attribute Compression
Learning-based methods have proven successful in compressing geometric information for point clouds. For attribute compression, however, they still lag behind non-learning-based methods such as the MPEG G-PCC standard. T…
AttributeComputational EfficiencyGenerative Adversarial NetworkChannel Compression: Rethinking Information Redundancy among Channels in CNN Architecture
Model compression and acceleration are attracting increasing attentions due to the demand for embedded devices and mobile applications. Research on efficient convolutional neural networks (CNNs) aims at removing feature …
Acoustic Scene ClassificationEvent Detectionimage-classificationImage Classification+3Sparse Tensor-based Multiscale Representation for Point Cloud Geometry Compression
This study develops a unified Point Cloud Geometry (PCG) compression method through the processing of multiscale sparse tensor-based voxelized PCG. We call this compression method SparsePCGC. The proposed SparsePCGC is a…
AttributeFully Convolutional One-Stage 3D Object Detection on LiDAR Range Images
We present a simple yet effective fully convolutional one-stage 3D object detector for LiDAR point clouds of autonomous driving scenes, termed FCOS-LiDAR. Unlike the dominant methods that use the bird-eye view (BEV), our…
3D Object DetectionAutonomous Drivingobject-detectionObject Detection+1