BAR — A Reinforcement Learning Agent for Bounding-Box Automated Refinement

Ayle, Morgane; Tekli, Jimmy; El-Zini, Julia; El-Asmar, Boulos; Awad, Mariette

doi:10.1609/aaai.v34i03.5639

Cited by 7 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To summarize, in these approaches, the state representation involves segmented image slices obtained from previous iterations of the vision algorithm or the DRL algorithm. Subsequently, the DRL agent predicts a series of bounding boxes to refine the object fit, leading to an updated state input and rewards based on intersection ratios [49,[51][52][53].…”

Section: Deep Reinforcement Learning In Object Detectionmentioning

confidence: 99%

A Task-Risk Consistency Object Detection Framework Based on Deep Reinforcement Learning

Wen,

Liu,

2023

Remote Sensing

View full text Add to dashboard Cite

A discernible gap has materialized between the expectations for object detection tasks in optical remote sensing images and the increasingly sophisticated design methods. The flexibility of deep learning object detection algorithms allows the selection and combination of multiple basic structures and model sizes, but this selection process relies heavily on human experience and lacks reliability when faced with special scenarios or extreme data distribution. To address these inherent challenges, this study proposes an approach that leverages deep reinforcement learning within the framework of vision tasks. This study introduces a Task-Risk Consistent Intelligent Detection Framework (TRC-ODF) for object detection in optical remote sensing images. The proposed framework designs a model optimization strategy based on deep reinforcement learning that systematically integrates the available information from images and vision processes. The core of the reinforcement learning agent is the proposed task-risk consistency reward mechanism, which is the driving force behind the optimal prediction allocation in the decision-making process. To verify the effectiveness of the proposed framework, multiple sets of empirical evaluations are conducted on representative optical remote sensing image datasets: RSOD, NWPU VHR-10, and DIOR. When applying the proposed framework to representative advanced detection models, the mean average precision (mAP@0.5 and mAP@0.5:0.95) is improved by 0.8–5.4 and 0.4–2.7, respectively. The obtained results showcase the considerable promise and potential of the TRC-ODF framework to address the challenges associated with object detection in optical remote sensing images.

show abstract

Section: Deep Reinforcement Learning In Object Detectionmentioning

confidence: 99%

A Task-Risk Consistency Object Detection Framework Based on Deep Reinforcement Learning

Wen,

Liu,

2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Instead of learning a policy from a large set of data, [15] proposed a method for bounding box refinement (BAR) using RL. In the paper, once the authors have an inaccurate bounding box that is predicted by some algorithm they use the BAR algorithm to predict a series of actions for refinement of a bounding box.…”

Section: Drl In Object Detectionmentioning

confidence: 99%

“…12. The figure illustrates a general implementation of object detection using DRL, where the state is an image segment cropped using a bounding box produced by some other algorithm or previous iteration of DRL, actions predicted by the DRL agent predict a series of bounding box transforma-tion to fit the object better, hence forming a new state and Reward is the improvement in Intersection over union (IOU) with iterations as used by [43], [25], [15], [386], [170], [275].…”

Section: Drl In Object Detectionmentioning

confidence: 99%

Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey

Le¹,

Rathour²,

Yamazaki³

et al. 2021

Preprint

View full text Add to dashboard Cite

Deep reinforcement learning augments the reinforcement learning framework and utilizes the powerful representation of deep neural networks. Recent works have demonstrated the remarkable successes of deep reinforcement learning in various domains including finance, medicine, healthcare, video games, robotics, and computer vision. In this work, we provide a detailed review of recent and state-of-the-art research advances of deep reinforcement learning in computer vision. We start with comprehending the theories of deep learning, reinforcement learning, and deep reinforcement learning. We then propose a categorization of deep reinforcement learning methodologies and discuss their advantages and limitations. In particular, we divide deep reinforcement learning into seven main categories according to their applications in computer vision, i.e. (i) landmark localization (ii) object detection; (iii) object tracking; (iv) registration on both 2D image and 3D image volumetric data (v) image segmentation; (vi) videos analysis; and (vii) other applications. Each of these categories is further analyzed with reinforcement learning techniques, network design, and performance. Moreover, we provide a comprehensive analysis of the existing publicly available datasets and examine source code availability. Finally, we present some open issues and discuss future research directions on deep reinforcement learning in computer vision.

show abstract