FcaNet: Frequency Channel Attention Networks
- URL: http://arxiv.org/abs/2012.11879v3
- Date: Thu, 4 Feb 2021 02:42:04 GMT
- Title: FcaNet: Frequency Channel Attention Networks
- Abstract summary: We rethink channel attention using frequency analysis.
We propose FcaNet with novel multi-spectral channel attention.
Our method could improve by 1.8% in terms of Top-1 accuracy on ImageNet.
- Score: 20.6292655895549
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Attention mechanism, especially channel attention, has gained great success
in the computer vision field. Many works focus on how to design efficient
channel attention mechanisms while ignoring a fundamental problem, i.e., using
global average pooling (GAP) as the unquestionable pre-processing method. In
this work, we start from a different view and rethink channel attention using
frequency analysis. Based on the frequency analysis, we mathematically prove
that the conventional GAP is a special case of the feature decomposition in the
frequency domain. With the proof, we naturally generalize the pre-processing of
channel attention mechanism in the frequency domain and propose FcaNet with
novel multi-spectral channel attention. The proposed method is simple but
effective. We can change only one line of code in the calculation to implement
our method within existing channel attention methods. Moreover, the proposed
method achieves state-of-the-art results compared with other channel attention
methods on image classification, object detection, and instance segmentation
tasks. Our method could improve by 1.8% in terms of Top-1 accuracy on ImageNet
compared with the baseline SENet-50, with the same number of parameters and the
same computational cost. Our code and models are publicly available at
https://github.com/cfzd/FcaNet.
Related papers
- Ensemble Quadratic Assignment Network for Graph Matching [52.20001802006391]
Graph matching is a commonly used technique in computer vision and pattern recognition.
Recent data-driven approaches have improved the graph matching accuracy remarkably.
We propose a graph neural network (GNN) based approach to combine the advantages of data-driven and traditional methods.
arXiv Detail & Related papers (2024-03-11T06:34:05Z) - OrthoNets: Orthogonal Channel Attention Networks [9.842943431749191]
We develop a new type of channel attention mechanism called OrthoNet.
Our results imply that an optimal choice of filter is elusive and generalization can be achieved.
Our code is publicly available at https://github.com/hady1011/OrthoNets/.
arXiv Detail & Related papers (2023-11-06T12:54:20Z) - Joint Channel Estimation and Feedback with Masked Token Transformers in
Massive MIMO Systems [74.52117784544758]
This paper proposes an encoder-decoder based network that unveils the intrinsic frequency-domain correlation within the CSI matrix.
The entire encoder-decoder network is utilized for channel compression.
Our method outperforms state-of-the-art channel estimation and feedback techniques in joint tasks.
arXiv Detail & Related papers (2023-06-08T06:15:17Z) - WaveNets: Wavelet Channel Attention Networks [9.842943431749191]
We propose Wavelet transform compression as a solution to the channel representation problem.
We generalize channel attention using Wavelet compression and name it WaveNet.
Our method outperforms the baseline SENet, and achieves the state-of-the-art results.
arXiv Detail & Related papers (2022-11-04T18:26:47Z) - Revisiting Random Channel Pruning for Neural Network Compression [159.99002793644163]
Channel (or 3D filter) pruning serves as an effective way to accelerate the inference of neural networks.
In this paper, we try to determine the channel configuration of the pruned models by random search.
We show that this simple strategy works quite well compared with other channel pruning methods.
arXiv Detail & Related papers (2022-05-11T17:59:04Z) - BA-Net: Bridge Attention for Deep Convolutional Neural Networks [4.459779019776622]
Bridge Attention Net (BA-Net) is proposed for better channel attention mechanisms.
BA-Net can not only provide richer features to calculate channel weight when feedforward, but also multiply paths of parameters updating when backforward.
arXiv Detail & Related papers (2021-12-08T07:39:18Z) - Robust MIMO Detection using Hypernetworks with Learned Regularizers [28.917679125825]
We propose a method that tries to strike a balance between symbol error rate (SER) performance and generality of channels.
Our method is based on hypernetworks that generate the parameters of a neural network-based detector that works well on a specific channel.
arXiv Detail & Related papers (2021-10-13T22:07:13Z) - Group Fisher Pruning for Practical Network Compression [58.25776612812883]
We present a general channel pruning approach that can be applied to various complicated structures.
We derive a unified metric based on Fisher information to evaluate the importance of a single channel and coupled channels.
Our method can be used to prune any structures including those with coupled channels.
arXiv Detail & Related papers (2021-08-02T08:21:44Z) - Channel-wise Knowledge Distillation for Dense Prediction [73.99057249472735]
We propose to align features channel-wise between the student and teacher networks.
We consistently achieve superior performance on three benchmarks with various network structures.
arXiv Detail & Related papers (2020-11-26T12:00:38Z) - Channel-wise Alignment for Adaptive Object Detection [66.76486843397267]
Generic object detection has been immensely promoted by the development of deep convolutional neural networks.
Existing methods on this task usually draw attention on the high-level alignment based on the whole image or object of interest.
In this paper, we realize adaptation from a thoroughly different perspective, i.e., channel-wise alignment.
arXiv Detail & Related papers (2020-09-07T02:42:18Z)
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.