Reinforcement Learning applications in computer vision?

Question

As I continued to study computer vision, I felt that RL (reinforcement learning) was used relatively less frequently in computer vision tasks, compared to the impact of the first RL and the likelihood that people predicted.

Even if you look at the list of papers accepted at top tier conferences such as CVPR, there are very few or no papers using RL. Why is RL not well used in computer vision?

Answer 1

RL has picked up significantly only in last few years. Reinforcement learning has been used both for solving applied tasks such as processing and analysis of visual information, and for solving specific computer vision problems such as filtering, extracting image features, localizing objects in scenes, and many others.

Last year there was a nice tutorial on Deep RL in CV at CVPR: http://ivg.au.tsinghua.edu.cn/DRLCV/

This is a list of interesting papers from various applications:

Visual Tracking

[1] James Supan?i?, III, Deva Ramanan, Tracking as Online Decision-Making: Learning a Policy From Streaming Videos With Reinforcement Learning, ICCV, 2017.

Visual Dialogue

[1] Abhishek Das, Satwik Kottur, José M. F. Moura, Stefan Lee, Dhruv Batra, earning Cooperative Visual Dialog Agents with Deep Reinforcement Learning, ICCV 2017.

Human Behaviour Analysis

[1] Nicholas Rhinehart, Kris M. Kitani, First-Person Activity Forecasting With Online Inverse Reinforcement Learning, ICCV, 2017.

Face Recognition

[1] Yongming Rao,Jiwen Lu, Jie Zhou. Attention-aware Deep Reinforcement Learning for Video Face Recognition, ICCV, 2017.

[2] Qingxing Cao, Liang Lin, Yukai Shi, Xiaodan Liang, Guanbin Li.Attention-Aware Face Hallucination via Deep Reinforcement Learning. CVPR, 2017.

Image Restoration

[1] Ke Yu, Chao Dong, Liang Lin, Chen Change Loy. Crafting a Toolchain for Image Restoration by Deep Reinforcement Learning. CVPR 2018.

Semantic Parsing

[1] Fangyu Liu, Shuaipeng Li, Liqiang Zhang, Chenghu Zhou, Rongtian Ye, Yuebin Wang, Jiwen Lu. 3DCNN-DQN-RNN: A Deep Reinforcement Learning Framework for Semantic Parsing of Large-Scale 3D Point Clouds. ICCV, 2017.

Video Summarization

[1] Kaiyang Zhou, Yu Qiao, Tao Xiang. Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward. AAAI, 2018.

Active Object localization

[1] Juan C. Caicedo, Svetlana Lazebnik. Active Object Localization with Deep Reinforcement Learning. ICCV, 2015.