Learning in the Frequency Domain
- URL: http://arxiv.org/abs/2002.12416v4
- Date: Tue, 31 Mar 2020 23:40:51 GMT
- Title: Learning in the Frequency Domain
- Authors: Kai Xu, Minghai Qin, Fei Sun, Yuhao Wang, Yen-Kuang Chen, Fengbo Ren
- Abstract summary: We propose a learning-based frequency selection method to identify the trivial frequency components which can be removed without accuracy loss.
Experiment results show that learning in the frequency domain with static channel selection can achieve higher accuracy than the conventional spatial downsampling approach.
- Score: 20.045740082113845
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Deep neural networks have achieved remarkable success in computer vision
tasks. Existing neural networks mainly operate in the spatial domain with fixed
input sizes. For practical applications, images are usually large and have to
be downsampled to the predetermined input size of neural networks. Even though
the downsampling operations reduce computation and the required communication
bandwidth, it removes both redundant and salient information obliviously, which
results in accuracy degradation. Inspired by digital signal processing
theories, we analyze the spectral bias from the frequency perspective and
propose a learning-based frequency selection method to identify the trivial
frequency components which can be removed without accuracy loss. The proposed
method of learning in the frequency domain leverages identical structures of
the well-known neural networks, such as ResNet-50, MobileNetV2, and Mask R-CNN,
while accepting the frequency-domain information as the input. Experiment
results show that learning in the frequency domain with static channel
selection can achieve higher accuracy than the conventional spatial
downsampling approach and meanwhile further reduce the input data size.
Specifically for ImageNet classification with the same input size, the proposed
method achieves 1.41% and 0.66% top-1 accuracy improvements on ResNet-50 and
MobileNetV2, respectively. Even with half input size, the proposed method still
improves the top-1 accuracy on ResNet-50 by 1%. In addition, we observe a 0.8%
average precision improvement on Mask R-CNN for instance segmentation on the
COCO dataset.
Related papers
- Automatic Network Adaptation for Ultra-Low Uniform-Precision
Quantization [6.1664476076961146]
Uniform-precision neural network quantization has gained popularity since it simplifies densely packed arithmetic unit for high computing capability.
It ignores heterogeneous sensitivity to the impact of quantization errors across the layers, resulting in sub-optimal inference.
This work proposes a novel neural architecture search called neural channel expansion that adjusts the network structure to alleviate accuracy degradation from ultra-low uniform-precision quantization.
arXiv Detail & Related papers (2022-12-21T09:41:25Z) - Increasing the Accuracy of a Neural Network Using Frequency Selective
Mesh-to-Grid Resampling [4.211128681972148]
We propose the use of keypoint frequency selective mesh-to-grid resampling (FSMR) for the processing of input data for neural networks.
We show that depending on the network architecture and classification task the application of FSMR during training aids learning process.
The classification accuracy can be increased by up to 4.31 percentage points for ResNet50 and the Oxflower17 dataset.
arXiv Detail & Related papers (2022-09-28T21:34:47Z) - CONet: Channel Optimization for Convolutional Neural Networks [33.58529066005248]
We study channel size optimization in convolutional neural networks (CNN)
We introduce an efficient dynamic scaling algorithm -- CONet -- that automatically optimize channel sizes across network layers for a given CNN.
We conduct experiments on CIFAR10/100 and ImageNet datasets and show that CONet can find efficient and accurate architectures searched in ResNet, DARTS, and DARTS+ spaces.
arXiv Detail & Related papers (2021-08-15T21:48:25Z) - SignalNet: A Low Resolution Sinusoid Decomposition and Estimation
Network [79.04274563889548]
We propose SignalNet, a neural network architecture that detects the number of sinusoids and estimates their parameters from quantized in-phase and quadrature samples.
We introduce a worst-case learning threshold for comparing the results of our network relative to the underlying data distributions.
In simulation, we find that our algorithm is always able to surpass the threshold for three-bit data but often cannot exceed the threshold for one-bit data.
arXiv Detail & Related papers (2021-06-10T04:21:20Z) - Broadcasted Residual Learning for Efficient Keyword Spotting [7.335747584353902]
We present a broadcasted residual learning method to achieve high accuracy with small model size and computational load.
We also propose a novel network architecture, Broadcasting-residual network (BC-ResNet), based on broadcasted residual learning.
BC-ResNets achieve state-of-the-art 98.0% and 98.7% top-1 accuracy on Google speech command datasets v1 and v2, respectively.
arXiv Detail & Related papers (2021-06-08T06:55:39Z) - Post-training deep neural network pruning via layer-wise calibration [70.65691136625514]
We propose a data-free extension of the approach for computer vision models based on automatically-generated synthetic fractal images.
When using real data, we are able to get a ResNet50 model on ImageNet with 65% sparsity rate in 8-bit precision in a post-training setting.
arXiv Detail & Related papers (2021-04-30T14:20:51Z) - Learning Frequency Domain Approximation for Binary Neural Networks [68.79904499480025]
We propose to estimate the gradient of sign function in the Fourier frequency domain using the combination of sine functions for training BNNs.
The experiments on several benchmark datasets and neural architectures illustrate that the binary network learned using our method achieves the state-of-the-art accuracy.
arXiv Detail & Related papers (2021-03-01T08:25:26Z) - Efficient Integer-Arithmetic-Only Convolutional Neural Networks [87.01739569518513]
We replace conventional ReLU with Bounded ReLU and find that the decline is due to activation quantization.
Our integer networks achieve equivalent performance as the corresponding FPN networks, but have only 1/4 memory cost and run 2x faster on modern GPU.
arXiv Detail & Related papers (2020-06-21T08:23:03Z) - Network Adjustment: Channel Search Guided by FLOPs Utilization Ratio [101.84651388520584]
This paper presents a new framework named network adjustment, which considers network accuracy as a function of FLOPs.
Experiments on standard image classification datasets and a wide range of base networks demonstrate the effectiveness of our approach.
arXiv Detail & Related papers (2020-04-06T15:51:00Z) - Centimeter-Level Indoor Localization using Channel State Information
with Recurrent Neural Networks [12.193558591962754]
This paper proposes the neural network method to estimate the centimeter-level indoor positioning with real CSI data collected from linear antennas.
It utilizes an amplitude of channel response or a correlation matrix as the input, which can highly reduce the data size and suppress the noise.
Also, it makes use of the consistency in the user motion trajectory via Recurrent Neural Network (RNN) and signal-noise ratio (SNR) information, which can further improve the estimation accuracy.
arXiv Detail & Related papers (2020-02-04T17:10:18Z) - Channel Assignment in Uplink Wireless Communication using Machine
Learning Approach [54.012791474906514]
This letter investigates a channel assignment problem in uplink wireless communication systems.
Our goal is to maximize the sum rate of all users subject to integer channel assignment constraints.
Due to high computational complexity, machine learning approaches are employed to obtain computational efficient solutions.
arXiv Detail & Related papers (2020-01-12T15:54:20Z)
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.