EMBANet: A Flexible Efffcient Multi-branch Attention Network

TL;DR

EMBANet introduces a flexible multi-branch attention module that enhances feature extraction in CNNs, leading to improved performance across classification, detection, and segmentation tasks.

Contribution

The paper proposes the MBC module and integrates it into a new backbone, EMBANet, offering adjustable multi-scale feature processing for attention networks.

Findings

EMBANet outperforms popular backbones in various vision tasks.

The MBC module provides flexible multi-scale feature representation.

EMBANet achieves superior accuracy in classification, detection, and segmentation.

Abstract

This work presents a novel module, namely multi-branch concat (MBC), to process the input tensor and obtain the multi-scale feature map. The proposed MBC module brings new degrees of freedom (DoF) for the design of attention networks by allowing the type of transformation operators and the number of branches to be flexibly adjusted. Two important transformation operators, multiplex and split, are considered in this work, both of which can represent multi-scale features at a more granular level and increase the range of receptive fields. By integrating the MBC and attention module, a multi-branch attention (MBA) module is consequently developed to capture the channel-wise interaction of feature maps for establishing the long-range channel dependency. By substituting the 3x3 convolutions in the bottleneck blocks of the ResNet with the proposed MBA, a novel block namely efficient multi-branch attention (EMBA) is obtained, which can be easily plugged into the state-of-the-art backbone CNN models. Furthermore, a new backbone network called EMBANet is established by stacking the EMBA blocks. The proposed EMBANet is extensively evaluated on representative computer vision tasks including: classification, detection, and segmentation. And it demonstrates consistently superior performance over the popular backbones.