WaveNets: Wavelet Channel Attention Networks

TL;DR

WaveNets introduce wavelet transform-based channel compression to enhance feature preservation in channel attention mechanisms, outperforming SENet and achieving state-of-the-art results in image classification.

Contribution

The paper proposes WaveNet, a novel channel attention mechanism utilizing wavelet transform compression to improve feature preservation and model inter-dependencies.

Findings

Wavelet transform is equivalent to recursive Haar wavelet transform.

WaveNet outperforms SENet on ImageNet classification.

Implementation is simple and can be integrated into existing models.

Abstract

Channel Attention reigns supreme as an effective technique in the field of computer vision. However, the proposed channel attention by SENet suffers from information loss in feature learning caused by the use of Global Average Pooling (GAP) to represent channels as scalars. Thus, designing effective channel attention mechanisms requires finding a solution to enhance features preservation in modeling channel inter-dependencies. In this work, we utilize Wavelet transform compression as a solution to the channel representation problem. We first test wavelet transform as an Auto-Encoder model equipped with conventional channel attention module. Next, we test wavelet transform as a standalone channel compression method. We prove that global average pooling is equivalent to the recursive approximate Haar wavelet transform. With this proof, we generalize channel attention using Wavelet compression and name it WaveNet. Implementation of our method can be embedded within existing channel attention methods with a couple of lines of code. We test our proposed method using ImageNet dataset for image classification task. Our method outperforms the baseline SENet, and achieves the state-of-the-art results. Our code implementation is publicly available at https://github.com/hady1011/WaveNet-C.