# Hierarchical Object Detection with Deep Reinforcement Learning

arXiv: https://arxiv.org/abs/1611.03718 · HTML: https://mlsanity.com/paper/1611.03718/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Nov 2016.

## Built on by (most cited first, 12 of 12)

- [AdaZoom: Adaptive Zoom Network for Multi-Scale Object Detection in Large Scenes](https://mlsanity.com/paper/2106.10409/) (2021)
- [Human-Machine Collaborative Video Coding Through Cuboidal Partitioning](https://mlsanity.com/paper/2102.01307/) (2021)
- [Sparsely ensembled convolutional neural network classifiers via reinforcement learning](https://mlsanity.com/paper/2102.03921/) (2021)
- [Visual Comfort Aware-Reinforcement Learning for Depth Adjustment of Stereoscopic 3D Images](https://mlsanity.com/paper/2104.06782/) (2021)
- [Object Detection with Deep Reinforcement Learning](https://mlsanity.com/paper/2208.04511/) (2022)
- [Adaptive Remote Sensing Image Attribute Learning for Active Object Detection](https://mlsanity.com/paper/2101.06438/) (2021)
- [A Reinforcement Learning Approach for Sequential Spatial Transformer Networks](https://mlsanity.com/paper/2106.14295/) (2021)
- [Integrating Saliency Ranking and Reinforcement Learning for Enhanced Object Detection](https://mlsanity.com/paper/2408.06803/) (2024)
- [Weakly Supervised Scene Text Detection using Deep Reinforcement Learning](https://mlsanity.com/paper/2201.04866/) (2022)
- [Reinforced Pedestrian Attribute Recognition with Group Optimization Reward](https://mlsanity.com/paper/2205.14042/) (2022)
- [Benchmarking Feature Extractors for Reinforcement Learning-Based Semiconductor Defect Localization](https://mlsanity.com/paper/2311.11145/) (2023)
- [Reinforced Compressive Neural Architecture Search for Versatile Adversarial Robustness](https://mlsanity.com/paper/2406.06792/) (2024)

## Abstract (arXiv)

We present a method for performing hierarchical object detection in images guided by a deep reinforcement learning agent. The key idea is to focus on those parts of the image that contain richer information and zoom on them. We train an intelligent agent that, given an image window, is capable of deciding where to focus the attention among five different predefined region candidates (smaller windows). This procedure is iterated providing a hierarchical image analysis.We compare two different candidate proposal strategies to guide the object search: with and without overlap. Moreover, our work compares two different strategies to extract features from a convolutional neural network for each region proposal: a first one that computes new feature maps for each region proposal, and a second one that computes the feature maps for the whole image to later generate crops for each region proposal. Experiments indicate better results for the overlapping candidate proposal strategy and a loss of performance for the cropped image features due to the loss of spatial resolution. We argue that, while this loss seems unavoidable when working with large amounts of object candidates, the much more reduced amount of region proposals generated by our reinforcement learning agent allows considering to extract features for each location without sharing convolutional computation among regions.