# AdaZoom: Adaptive Zoom Network for Multi-Scale Object Detection in Large Scenes

arXiv: https://arxiv.org/abs/2106.10409 · HTML: https://mlsanity.com/paper/2106.10409/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 48 references that are in the map.
- First posted on arXiv 19 Jun 2021.

## Builds on (most cited first, 30 of 32)

- [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)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [CornerNet: Detecting Objects as Paired Keypoints](https://mlsanity.com/paper/1808.01244/) (2018)
- [Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition](https://mlsanity.com/paper/1406.4729/) (2014)
- [DOTA: A Large-scale Dataset for Object Detection in Aerial Images](https://mlsanity.com/paper/1711.10398/) (2017)
- [R-FCN: Object Detection via Region-based Fully Convolutional Networks](https://mlsanity.com/paper/1605.06409/) (2016)
- [The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking](https://mlsanity.com/paper/1804.00518/) (2018)
- [An Analysis of Scale Invariance in Object Detection - SNIP](https://mlsanity.com/paper/1711.08189/) (2017)
- [SNIPER: Efficient Multi-Scale Training](https://mlsanity.com/paper/1805.09300/) (2018)
- [A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection](https://mlsanity.com/paper/1607.07155/) (2016)
- [Clustered Object Detection in Aerial Images](https://mlsanity.com/paper/1904.08008/) (2019)
- [Vision Meets Drones: A Challenge](https://mlsanity.com/paper/1804.07437/) (2018)
- [Density Map Guided Object Detection in Aerial Images](https://mlsanity.com/paper/2004.05520/) (2020)
- [AugFPN: Improving Multi-scale Feature Learning for Object Detection](https://mlsanity.com/paper/1912.05384/) (2019)
- [AutoFocus: Efficient Multi-Scale Inference](https://mlsanity.com/paper/1812.01600/) (2018)
- [Learning When and Where to Zoom with Deep Reinforcement Learning](https://mlsanity.com/paper/2003.00425/) (2020)
- [Active Object Localization with Deep Reinforcement Learning](https://mlsanity.com/paper/1511.06015/) (2015)
- [Dynamic Zoom-in Network for Fast Object Detection in Large Images](https://mlsanity.com/paper/1711.05187/) (2017)
- [Object Detection Networks on Convolutional Feature Maps](https://mlsanity.com/paper/1504.06066/) (2015)
- [Hierarchical Object Detection with Deep Reinforcement Learning](https://mlsanity.com/paper/1611.03718/) (2016)
- [AttentionNet: Aggregating Weak Directions for Accurate Object Detection](https://mlsanity.com/paper/1506.07704/) (2015)
- [Object-sensitive Deep Reinforcement Learning](https://mlsanity.com/paper/1809.06064/) (2018)
- [Collaborative Deep Reinforcement Learning for Joint Object Search](https://mlsanity.com/paper/1702.05573/) (2017)

## Built on by (most cited first, 11 of 11)

- [Towards Large-Scale Small Object Detection: Survey and Benchmarks](https://mlsanity.com/paper/2207.14096/) (2022)
- [Focus-and-Detect: A Small Object Detection Framework for Aerial Images](https://mlsanity.com/paper/2203.12976/) (2022)
- [FLOAT: Factorized Learning of Object Attributes for Improved Multi-object Multi-part Scene Parsing](https://mlsanity.com/paper/2203.16168/) (2022)
- [AdaFPP: Adapt-Focused Bi-Propagating Prototype Learning for Panoramic Activity Recognition](https://mlsanity.com/paper/2405.02538/) (2024)
- [Adaptive Image Zoom-in with Bounding Box Transformation for UAV Object Detection](https://mlsanity.com/paper/2602.07512/) (2026)
- [Mastering Spatial Graph Prediction of Road Networks](https://mlsanity.com/paper/2210.00828/) (2022)
- [Resource Efficient Perception for Vision Systems](https://mlsanity.com/paper/2405.07166/) (2024)
- [Small Object Detection Model with Spatial Laplacian Pyramid Attention and Multi-Scale Features Enhancement in Aerial Images](https://mlsanity.com/paper/2602.23031/) (2026)
- [DenseScout: Algorithm-System Co-design for Budgeted Tiny Object Selection on Edge Platforms](https://mlsanity.com/paper/2604.25300/) (2026)
- [FlashNormal: Detailed Surface Normal Estimation from Flash and No-Flash Images](https://mlsanity.com/paper/2608.25360/) (2026)
- [Variable-Granularity Tokenization for High-Resolution Object Detection](https://mlsanity.com/paper/2608.28706/) (2026)

## Abstract (arXiv)

Detection in large-scale scenes is a challenging problem due to small objects and extreme scale variation. It is essential to focus on the image regions of small objects. In this paper, we propose a novel Adaptive Zoom (AdaZoom) network as a selective magnifier with flexible shape and focal length to adaptively zoom the focus regions for object detection. Based on policy gradient, we construct a reinforcement learning framework for focus region generation, with the reward formulated by object distributions. The scales and aspect ratios of the generated regions are adaptive to the scales and distribution of objects inside. We apply variable magnification according to the scale of the region for adaptive multi-scale detection. We further propose collaborative training to complementarily promote the performance of AdaZoom and the detection network. To validate the effectiveness, we conduct extensive experiments on VisDrone2019, UAVDT, and DOTA datasets. The experiments show AdaZoom brings a consistent and significant improvement over different detection networks, achieving state-of-the-art performance on these datasets, especially outperforming the existing methods by AP of 4.64% on Vis-Drone2019.