# Deep Feature Pyramid Reconfiguration for Object Detection

arXiv: https://arxiv.org/abs/1808.07993 · HTML: https://mlsanity.com/paper/1808.07993/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Aug 2018.

## Built on by (most cited first, 23 of 23)

- [You Only Look One-level Feature](https://mlsanity.com/paper/2103.09460/) (2021)
- [HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View Reconstruction](https://mlsanity.com/paper/2410.06245/) (2024)
- [Localization Distillation for Dense Object Detection](https://mlsanity.com/paper/2102.12252/) (2021)
- [Attention, please! A survey of Neural Attention Models in Deep Learning](https://mlsanity.com/paper/2103.16775/) (2021)
- [GraphFPN: Graph Feature Pyramid Network for Object Detection](https://mlsanity.com/paper/2108.00580/) (2021)
- [Localization Distillation for Object Detection](https://mlsanity.com/paper/2204.05957/) (2022)
- [Tri2-plane: Thinking Head Avatar via Feature Pyramid](https://mlsanity.com/paper/2401.09386/) (2024)
- [Circle Representation for Medical Object Detection](https://mlsanity.com/paper/2110.12093/) (2021)
- [Person Re-identification via Attention Pyramid](https://mlsanity.com/paper/2108.05340/) (2021)
- [You Should Look at All Objects](https://mlsanity.com/paper/2207.07889/) (2022)
- [Towards Balanced Learning for Instance Recognition](https://mlsanity.com/paper/2108.10175/) (2021)
- [Precise Single-stage Detector](https://mlsanity.com/paper/2210.04252/) (2022)
- [Convolutional Neural Networks with Gated Recurrent Connections](https://mlsanity.com/paper/2106.02859/) (2021)
- [Detail Preserving Residual Feature Pyramid Modules for Optical Flow](https://mlsanity.com/paper/2107.10990/) (2021)
- [RCNet: Reverse Feature Pyramid and Cross-scale Shift Network for Object Detection](https://mlsanity.com/paper/2110.12130/) (2021)
- [Revisiting the Loss Weight Adjustment in Object Detection](https://mlsanity.com/paper/2103.09488/) (2021)
- [A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets](https://mlsanity.com/paper/2107.07927/) (2021)
- [YOLO-RS: Remote Sensing Enhanced Crop Detection Methods](https://mlsanity.com/paper/2504.11165/) (2025)
- [Adaptive Dilated Convolution For Human Pose Estimation](https://mlsanity.com/paper/2107.10477/) (2021)
- [RelationRS: Relationship Representation Network for Object Detection in Aerial Images](https://mlsanity.com/paper/2110.06730/) (2021)
- [Selective Multi-Scale Learning for Object Detection](https://mlsanity.com/paper/2206.08206/) (2022)
- [Delving into the Scale Variance Problem in Object Detection](https://mlsanity.com/paper/2206.08227/) (2022)
- [A lightweight YOLOv5-FFM model for occlusion pedestrian detection](https://mlsanity.com/paper/2408.06633/) (2024)

## Abstract (arXiv)

State-of-the-art object detectors usually learn multi-scale representations to get better results by employing feature pyramids. However, the current designs for feature pyramids are still inefficient to integrate the semantic information over different scales. In this paper, we begin by investigating current feature pyramids solutions, and then reformulate the feature pyramid construction as the feature reconfiguration process. Finally, we propose a novel reconfiguration architecture to combine low-level representations with high-level semantic features in a highly-nonlinear yet efficient way. In particular, our architecture which consists of global attention and local reconfigurations, is able to gather task-oriented features across different spatial locations and scales, globally and locally. Both the global attention and local reconfiguration are lightweight, in-place, and end-to-end trainable. Using this method in the basic SSD system, our models achieve consistent and significant boosts compared with the original model and its other variations, without losing real-time processing speed.