Object Detection with Deep Reinforcement Learning
This work addresses object detection for computer vision applications, but it appears incremental as it builds on existing reinforcement learning formulations without introducing a major breakthrough.
The paper tackles object localization by implementing a deep reinforcement learning algorithm and compares hierarchical and dynamic action settings, achieving performance improvements through ablation studies on hyperparameters and architectures.
Object localization has been a crucial task in computer vision field. Methods of localizing objects in an image have been proposed based on the features of the attended pixels. Recently researchers have proposed methods to formulate object localization as a dynamic decision process, which can be solved by a reinforcement learning approach. In this project, we implement a novel active object localization algorithm based on deep reinforcement learning. We compare two different action settings for this MDP: a hierarchical method and a dynamic method. We further perform some ablation studies on the performance of the models by investigating different hyperparameters and various architecture changes.