# A^2-FPN: Attention Aggregation based Feature Pyramid Network for Instance Segmentation

arXiv: https://arxiv.org/abs/2105.03186 · HTML: https://mlsanity.com/paper/2105.03186/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 41 references that are in the map.
- First posted on arXiv 7 May 2021.

## Builds on (most cited first, 30 of 37)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [Dual Attention Network for Scene Segmentation](https://mlsanity.com/paper/1809.02983/) (2018)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [Hybrid Task Cascade for Instance Segmentation](https://mlsanity.com/paper/1901.07518/) (2019)
- [GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond](https://mlsanity.com/paper/1904.11492/) (2019)
- [NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection](https://mlsanity.com/paper/1904.07392/) (2019)
- [Mask Scoring R-CNN](https://mlsanity.com/paper/1903.00241/) (2019)
- [Associative Embedding: End-to-End Learning for Joint Detection and Grouping](https://mlsanity.com/paper/1611.05424/) (2016)
- [ParseNet: Looking Wider to See Better](https://mlsanity.com/paper/1506.04579/) (2015)
- [Fully Convolutional Instance-aware Semantic Segmentation](https://mlsanity.com/paper/1611.07709/) (2016)
- [Instance-aware Semantic Segmentation via Multi-task Network Cascades](https://mlsanity.com/paper/1512.04412/) (2015)
- [Graph-Based Global Reasoning Networks](https://mlsanity.com/paper/1811.12814/) (2018)
- [CARAFE: Content-Aware ReAssembly of FEatures](https://mlsanity.com/paper/1905.02188/) (2019)
- [Semantic Instance Segmentation with a Discriminative Loss Function](https://mlsanity.com/paper/1708.02551/) (2017)
- [Learning to Segment Object Candidates](https://mlsanity.com/paper/1506.06204/) (2015)
- [Deep Watershed Transform for Instance Segmentation](https://mlsanity.com/paper/1611.08303/) (2016)

## Built on by (most cited first, 15 of 15)

- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks](https://mlsanity.com/paper/2206.06637/) (2022)
- [Recurrent Generic Contour-based Instance Segmentation with Progressive Learning](https://mlsanity.com/paper/2301.08898/) (2023)
- [Retro-FPN: Retrospective Feature Pyramid Network for Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2308.09314/) (2023)
- [An Effective and Robust Detector for Logo Detection](https://mlsanity.com/paper/2108.00422/) (2021)
- [Attention-Aware Anime Line Drawing Colorization](https://mlsanity.com/paper/2212.10988/) (2022)
- [TripOptimizer: Generative 3D Shape Optimization and Drag Prediction using Triplane VAE Networks](https://mlsanity.com/paper/2509.12224/) (2025)
- [FA-YOLO: Research On Efficient Feature Selection YOLO Improved Algorithm Based On FMDS and AGMF Modules](https://mlsanity.com/paper/2408.16313/) (2024)
- [P2HCT: Plug-and-Play Hierarchical C2F Transformer for Multi-Scale Feature Fusion](https://mlsanity.com/paper/2505.12772/) (2025)
- [Context-Enhanced Detector For Building Detection From Remote Sensing Images](https://mlsanity.com/paper/2310.07638/) (2023)
- [BAFPN: Bi directional alignment of features to improve localization accuracy](https://mlsanity.com/paper/2412.01859/) (2024)
- [Generic Multimodal Spatially Graph Network for Spatially Embedded Network Representation Learning](https://mlsanity.com/paper/2502.00530/) (2025)
- [A3-FPN: Asymptotic Content-Aware Pyramid Attention Network for Dense Visual Prediction](https://mlsanity.com/paper/2604.10210/) (2026)
- [MPerS: Dynamic MLLM MixExperts Perception-Guided Remote Sensing Scene Segmentation](https://mlsanity.com/paper/2605.10769/) (2026)
- [Context-Guided Semantic Alignment for Feature Fusion Networks](https://mlsanity.com/paper/2606.14005/) (2026)

## Abstract (arXiv)

Learning pyramidal feature representations is crucial for recognizing object instances at different scales. Feature Pyramid Network (FPN) is the classic architecture to build a feature pyramid with high-level semantics throughout. However, intrinsic defects in feature extraction and fusion inhibit FPN from further aggregating more discriminative features. In this work, we propose Attention Aggregation based Feature Pyramid Network (A^2-FPN), to improve multi-scale feature learning through attention-guided feature aggregation. In feature extraction, it extracts discriminative features by collecting-distributing multi-level global context features, and mitigates the semantic information loss due to drastically reduced channels. In feature fusion, it aggregates complementary information from adjacent features to generate location-wise reassembly kernels for content-aware sampling, and employs channel-wise reweighting to enhance the semantic consistency before element-wise addition. A^2-FPN shows consistent gains on different instance segmentation frameworks. By replacing FPN with A^2-FPN in Mask R-CNN, our model boosts the performance by 2.1% and 1.6% mask AP when using ResNet-50 and ResNet-101 as backbone, respectively. Moreover, A^2-FPN achieves an improvement of 2.0% and 1.4% mask AP when integrated into the strong baselines such as Cascade Mask R-CNN and Hybrid Task Cascade.