# Attentional Feature Fusion

Source: [Attentional Feature Fusion](<https://www.sota2.com/research/paper/68fa68bc1e209131cea1de54>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T04:10:29.690Z

Authors: Yimian Dai, Fabian Gieseke, Stefan Oehmcke, Yiquan Wu, Kobus Barnard

Published: 2020-09-29T15:10:18.000Z

## Abstract

Feature fusion, the combination of features from different layers or branches, is an omnipresent part of modern network architectures. It is often implemented via simple operations, such as summation or concatenation, but this might not be the best choice. In this work, we propose a uniform and general scheme, namely attentional feature fusion, which is applicable for most common scenarios, including feature fusion induced by short and long skip connections as well as within Inception layers. To better fuse features of inconsistent semantics and scales, we propose a multi-scale channel attention module, which addresses issues that arise when fusing features given at different scales. We also demonstrate that the initial integration of feature maps can become a bottleneck and that this issue can be alleviated by adding another level of attention, which we refer to as iterative attentional feature fusion. With fewer layers or parameters, our models outperform state-of-the-art networks on both CIFAR-100 and ImageNet datasets, which suggests that more sophisticated attention mechanisms for feature fusion hold great potential to consistently yield better results compared to their direct counterparts. Our codes and trained models are available online.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Classification on ImageNet (val)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-val.md>): Image Classification; ImageNet (val); Top-1 Acc: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2009.14082>)

[PDF](<https://arxiv.org/pdf/2009.14082.pdf>)

[Implementation](<https://github.com/YimianDai/open-aff>)
