Object Detection with Deep Reinforcement Learning

TL;DR

This paper introduces a novel deep reinforcement learning approach for active object localization, comparing hierarchical and dynamic action strategies, and analyzing the impact of hyperparameters and architecture choices.

Contribution

It presents a new deep reinforcement learning algorithm for object localization and evaluates different action settings and model configurations.

Findings

Hierarchical and dynamic action strategies are effective for object localization.

Hyperparameters significantly influence model performance.

Architecture modifications impact localization accuracy.

Abstract

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.