# Attentional Feature Fusion

arXiv: https://arxiv.org/abs/2009.14082 · HTML: https://mlsanity.com/paper/2009.14082/

## Key facts

- Cited by 115 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Sep 2020.

## Built on by (most cited first, 30 of 115)

- [Context-aware Cross-level Fusion Network for Camouflaged Object Detection](https://mlsanity.com/paper/2105.12555/) (2021)
- [Changer: Feature Interaction is What You Need for Change Detection](https://mlsanity.com/paper/2209.08290/) (2022)
- [Contrastive Semi-supervised Learning for Underwater Image Restoration via Reliable Bank](https://mlsanity.com/paper/2303.09101/) (2023)
- [CoLa-Diff: Conditional Latent Diffusion Model for Multi-Modal MRI Synthesis](https://mlsanity.com/paper/2303.14081/) (2023)
- [CRS-Diff: Controllable Remote Sensing Image Generation with Diffusion Model](https://mlsanity.com/paper/2403.11614/) (2024)
- [BiCnet-TKS: Learning Efficient Spatial-Temporal Representation for Video Person Re-Identification](https://mlsanity.com/paper/2104.14783/) (2021)
- [Surgical-VQLA: Transformer with Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery](https://mlsanity.com/paper/2305.11692/) (2023)
- [MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection](https://mlsanity.com/paper/2112.03902/) (2021)
- [HVTR: Hybrid Volumetric-Textural Rendering for Human Avatars](https://mlsanity.com/paper/2112.10203/) (2021)
- [Camouflaged Object Detection via Context-aware Cross-level Fusion](https://mlsanity.com/paper/2207.13362/) (2022)
- [DA-DETR: Domain Adaptive Detection Transformer with Information Fusion](https://mlsanity.com/paper/2103.17084/) (2021)
- [Learnable Expansion of Graph Operators for Multi-Modal Feature Fusion](https://mlsanity.com/paper/2410.01506/) (2024)
- [Bi-level Feature Alignment for Versatile Image Translation and Manipulation](https://mlsanity.com/paper/2107.03021/) (2021)
- [CoBEV: Elevating Roadside 3D Object Detection with Depth and Height Complementarity](https://mlsanity.com/paper/2310.02815/) (2023)
- [Vision-Language Modeling Meets Remote Sensing: Models, Datasets and Perspectives](https://mlsanity.com/paper/2505.14361/) (2025)
- [Pick of the Bunch: Detecting Infrared Small Targets Beyond Hit-Miss Trade-Offs via Selective Rank-Aware Attention](https://mlsanity.com/paper/2408.03717/) (2024)
- [Multi-modal Depression Estimation based on Sub-attentional Fusion](https://mlsanity.com/paper/2207.06180/) (2022)
- [Skeleton-based Action Recognition via Temporal-Channel Aggregation](https://mlsanity.com/paper/2205.15936/) (2022)
- [DSRC: Learning Density-insensitive and Semantic-aware Collaborative Representation against Corruptions](https://mlsanity.com/paper/2412.10739/) (2024)
- [YOLO-ReT: Towards High Accuracy Real-time Object Detection on Edge GPUs](https://mlsanity.com/paper/2110.13713/) (2021)
- [Edge-Aware Mirror Network for Camouflaged Object Detection](https://mlsanity.com/paper/2307.03932/) (2023)
- [EDPN: Enhanced Deep Pyramid Network for Blurry Image Restoration](https://mlsanity.com/paper/2105.04872/) (2021)
- [DualBEV: Unifying Dual View Transformation with Probabilistic Correspondences](https://mlsanity.com/paper/2403.05402/) (2024)
- [D-Net: Dynamic Large Kernel with Dynamic Feature Fusion for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/2403.10674/) (2024)
- [LLMRA: Multi-modal Large Language Model based Restoration Assistant](https://mlsanity.com/paper/2401.11401/) (2024)
- [Cross-spectral Gated-RGB Stereo Depth Estimation](https://mlsanity.com/paper/2405.12759/) (2024)
- [Underwater Object Detection in the Era of Artificial Intelligence: Current, Challenge, and Future](https://mlsanity.com/paper/2410.05577/) (2024)
- [Seeing Through the Noise: Improving Infrared Small Target Detection and Segmentation from Noise Suppression Perspective](https://mlsanity.com/paper/2508.06878/) (2025)
- [In-Bed Human Pose Estimation from Unseen and Privacy-Preserving Image Domains](https://mlsanity.com/paper/2111.15124/) (2021)
- [Pixel-aligned RGB-NIR Stereo Imaging and Dataset for Robot Vision](https://mlsanity.com/paper/2411.18025/) (2024)

## Abstract (arXiv)

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.