# Multi-patch Feature Pyramid Network for Weakly Supervised Object Detection in Optical Remote Sensing Images

arXiv: https://arxiv.org/abs/2108.08063 · HTML: https://mlsanity.com/paper/2108.08063/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 50 references that are in the map.
- First posted on arXiv 18 Aug 2021.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [Regularized Evolution for Image Classifier Architecture Search](https://mlsanity.com/paper/1802.01548/) (2018)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [DOTA: A Large-scale Dataset for Object Detection in Aerial Images](https://mlsanity.com/paper/1711.10398/) (2017)
- [CNN Features off-the-shelf: an Astounding Baseline for Recognition](https://mlsanity.com/paper/1403.6382/) (2014)
- [NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection](https://mlsanity.com/paper/1904.07392/) (2019)
- [Weakly Supervised Deep Detection Networks](https://mlsanity.com/paper/1511.02853/) (2015)
- [More Diverse Means Better: Multimodal Deep Learning Meets Remote Sensing Imagery Classification](https://mlsanity.com/paper/2008.05457/) (2020)
- [Multiple Instance Detection Network with Online Instance Classifier Refinement](https://mlsanity.com/paper/1704.00138/) (2017)
- [Graph Convolutional Networks for Hyperspectral Image Classification](https://mlsanity.com/paper/2008.02457/) (2020)
- [A Survey on Object Detection in Optical Remote Sensing Images](https://mlsanity.com/paper/1603.06201/) (2016)
- [C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection](https://mlsanity.com/paper/1904.05647/) (2019)
- [An Augmented Linear Mixing Model to Address Spectral Variability for Hyperspectral Unmixing](https://mlsanity.com/paper/1810.12000/) (2018)
- [Nested Network with Two-Stream Pyramid for Salient Object Detection in Optical Remote Sensing Images](https://mlsanity.com/paper/1906.08462/) (2019)
- [Min-Entropy Latent Model for Weakly Supervised Object Detection](https://mlsanity.com/paper/1902.06057/) (2019)
- [ORSIm Detector: A Novel Object Detection Framework in Optical Remote Sensing Imagery Using Spatial-Frequency Channel Features](https://mlsanity.com/paper/1901.07925/) (2019)
- [Weakly Supervised Attention Pyramid Convolutional Neural Network for Fine-Grained Visual Classification](https://mlsanity.com/paper/2002.03353/) (2020)
- [On learning to localize objects with minimal supervision](https://mlsanity.com/paper/1403.1024/) (2014)
- [Dynamic Feature Fusion for Semantic Edge Detection](https://mlsanity.com/paper/1902.09104/) (2019)
- [Road Segmentation for Remote Sensing Images using Adversarial Spatial Pyramid Networks](https://mlsanity.com/paper/2008.04021/) (2020)
- [Fourier-based Rotation-invariant Feature Boosting: An Efficient Framework for Geospatial Object Detection](https://mlsanity.com/paper/1905.11074/) (2019)
- [Invariant Attribute Profiles: A Spatial-Frequency Joint Feature Extractor for Hyperspectral Image Classification](https://mlsanity.com/paper/1912.08847/) (2019)
- [A novel Deep Structure U-Net for Sea-Land Segmentation in Remote Sensing Images](https://mlsanity.com/paper/2003.07784/) (2020)
- [AMIL: Adversarial Multi Instance Learning for Human Pose Estimation](https://mlsanity.com/paper/2003.08002/) (2020)

## Built on by (most cited first, 7 of 7)

- [Remote Sensing Object Detection Meets Deep Learning: A Meta-review of Challenges and Advances](https://mlsanity.com/paper/2309.06751/) (2023)
- [TransY-Net:Learning Fully Transformer Networks for Change Detection of Remote Sensing Images](https://mlsanity.com/paper/2310.14214/) (2023)
- [A Comparative Review of Recent Few-Shot Object Detection Algorithms](https://mlsanity.com/paper/2111.00201/) (2021)
- [Efficient Object Detection in Optical Remote Sensing Imagery via Attention-based Feature Distillation](https://mlsanity.com/paper/2310.18676/) (2023)
- [Fourier Angle Alignment for Oriented Object Detection in Remote Sensing](https://mlsanity.com/paper/2602.23790/) (2026)
- [Enhanced Single-shot Detector for Small Object Detection in Remote Sensing Images](https://mlsanity.com/paper/2205.05927/) (2022)
- [HMR-Net: Hierarchical Modular Routing for Cross-Domain Object Detection in Aerial Images](https://mlsanity.com/paper/2604.18866/) (2026)

## Abstract (arXiv)

Object detection is a challenging task in remote sensing because objects only occupy a few pixels in the images, and the models are required to simultaneously learn object locations and detection. Even though the established approaches well perform for the objects of regular sizes, they achieve weak performance when analyzing small ones or getting stuck in the local minima (e.g. false object parts). Two possible issues stand in their way. First, the existing methods struggle to perform stably on the detection of small objects because of the complicated background. Second, most of the standard methods used hand-crafted features, and do not work well on the detection of objects parts of which are missing. We here address the above issues and propose a new architecture with a multiple patch feature pyramid network (MPFP-Net). Different from the current models that during training only pursue the most discriminative patches, in MPFPNet the patches are divided into class-affiliated subsets, in which the patches are related and based on the primary loss function, a sequence of smooth loss functions are determined for the subsets to improve the model for collecting small object parts. To enhance the feature representation for patch selection, we introduce an effective method to regularize the residual values and make the fusion transition layers strictly norm-preserving. The network contains bottom-up and crosswise connections to fuse the features of different scales to achieve better accuracy, compared to several state-of-the-art object detection models. Also, the developed architecture is more efficient than the baselines.