# Learning Region Features for Object Detection

arXiv: https://arxiv.org/abs/1803.07066 · HTML: https://mlsanity.com/paper/1803.07066/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Mar 2018.

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

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Group-Free 3D Object Detection via Transformers](https://mlsanity.com/paper/2104.00678/) (2021)
- [Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification](https://mlsanity.com/paper/2108.08728/) (2021)
- [Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibration](https://mlsanity.com/paper/2109.14285/) (2021)
- [Temporal RoI Align for Video Object Recognition](https://mlsanity.com/paper/2109.03495/) (2021)
- [Learning Inner-Group Relations on Point Clouds](https://mlsanity.com/paper/2108.12468/) (2021)
- [Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networks](https://mlsanity.com/paper/2109.12872/) (2021)
- [GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNs](https://mlsanity.com/paper/2210.10758/) (2022)
- [Centroid Transformers: Learning to Abstract with Attention](https://mlsanity.com/paper/2102.08606/) (2021)
- [IAFA: Instance-aware Feature Aggregation for 3D Object Detection from a Single Image](https://mlsanity.com/paper/2103.03480/) (2021)
- [Survey of Image Based Graph Neural Networks](https://mlsanity.com/paper/2106.06307/) (2021)
- [Automatic Relation-aware Graph Network Proliferation](https://mlsanity.com/paper/2205.15678/) (2022)
- [Spatiotemporal Transformer Attention Network for 3D Voxel Level Joint Segmentation and Motion Prediction in Point Cloud](https://mlsanity.com/paper/2203.00138/) (2022)
- [Deep representation learning: Fundamentals, Perspectives, Applications, and Open Challenges](https://mlsanity.com/paper/2211.14732/) (2022)
- [Spatio-Temporal driven Attention Graph Neural Network with Block Adjacency matrix (STAG-NN-BA) for Remote Land-use Change Detection](https://mlsanity.com/paper/2303.14322/) (2023)

## Abstract (arXiv)

While most steps in the modern object detection methods are learnable, the region feature extraction step remains largely hand-crafted, featured by RoI pooling methods. This work proposes a general viewpoint that unifies existing region feature extraction methods and a novel method that is end-to-end learnable. The proposed method removes most heuristic choices and outperforms its RoI pooling counterparts. It moves further towards fully learnable object detection.