# Tree-Structured Reinforcement Learning for Sequential Object Localization

arXiv: https://arxiv.org/abs/1703.02710 · HTML: https://mlsanity.com/paper/1703.02710/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Mar 2017.

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

- [Weakly Supervised Object Localization and Detection: A Survey](https://mlsanity.com/paper/2104.07918/) (2021)
- [Deep reinforcement learning in medical imaging: A literature review](https://mlsanity.com/paper/2103.05115/) (2021)
- [Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Bounding Boxes via Reinforcement Learning](https://mlsanity.com/paper/2207.11934/) (2022)
- [Sequential Voting with Relational Box Fields for Active Object Detection](https://mlsanity.com/paper/2110.11524/) (2021)
- [Video Violence Recognition and Localization Using a Semi-Supervised Hard Attention Model](https://mlsanity.com/paper/2202.02212/) (2022)
- [Dynamic Multi-Scale Loss Optimization for Object Detection](https://mlsanity.com/paper/2108.04014/) (2021)
- [Adaptive Remote Sensing Image Attribute Learning for Active Object Detection](https://mlsanity.com/paper/2101.06438/) (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)
- [Learning Transferable Reward for Query Object Localization with Policy Adaptation](https://mlsanity.com/paper/2202.12403/) (2022)
- [An Adaptive Threshold for the Canny Edge Detection with Actor-Critic Algorithm](https://mlsanity.com/paper/2209.08699/) (2022)
- [Utilizing Reinforcement Learning for Bottom-Up part-wise Reconstruction of 2D Wire-Frame Projections](https://mlsanity.com/paper/2503.16629/) (2025)

## Abstract (arXiv)

Existing object proposal algorithms usually search for possible object regions over multiple locations and scales separately, which ignore the interdependency among different objects and deviate from the human perception procedure. To incorporate global interdependency between objects into object localization, we propose an effective Tree-structured Reinforcement Learning (Tree-RL) approach to sequentially search for objects by fully exploiting both the current observation and historical search paths. The Tree-RL approach learns multiple searching policies through maximizing the long-term reward that reflects localization accuracies over all the objects. Starting with taking the entire image as a proposal, the Tree-RL approach allows the agent to sequentially discover multiple objects via a tree-structured traversing scheme. Allowing multiple near-optimal policies, Tree-RL offers more diversity in search paths and is able to find multiple objects with a single feed-forward pass. Therefore, Tree-RL can better cover different objects with various scales which is quite appealing in the context of object proposal. Experiments on PASCAL VOC 2007 and 2012 validate the effectiveness of the Tree-RL, which can achieve comparable recalls with current object proposal algorithms via much fewer candidate windows.