Reinforcement Learning for Visual Object Detection

By Stefan Mathe, Aleksis Pirinen, Cristian Sminchisescu. 2016

170 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Glimpse Clouds: Human Activity Recognition from Unstructured Feature Points (2018, neutral): “Similar hard attention was used in multiple object recognition [2], object localization [7, 38, 23], saliency map generation [27], and action detection [60].”
Spatial Memory for Context Reasoning in Object Detection (2017, background): “An interesting recent direction focuses on using deep reinforcement learning (DRL) to optimize the sequence selection problem in detection [6, 9, 50, 61].”
Tree-Structured Reinforcement Learning for Sequential Object Localization (2016, background): “Another type of works attempts [11–14] to reduce the number of windows with an active object detection strategy.”
Deep Reinforcement Learning (2018, background): “search for objects sequentially, considering both the current observation and previous search paths, by maximizing the long-term reward associated with localization accuracy over all objects with DQN.Mathe et al. (2016) propose to use policy search for visual object detection.Kong et al.(2017) deplo”
AutoFocus: Efficient Multi-Scale Inference (2018, background): “easier task and does not require instance-level reasoning. AutoFocus shares the motivation with saliency and reinforcement learning based methods which perform a guided search while processing images [28,26,42,53,23,49,55,29,47], but it is designed to predict small objects in coarser scales and they”
Saliency-based Sequential Image Attention with Multiset Prediction (2017, methodology): “While we focus on using reinforcement learning for multiset classification with only class labels as annotation, RL has been applied to other computer vision tasks, including modeling eye movements based on annotated human scan paths [29], optimizing prediction performance subject to a computational”
Deep Reinforcement Learning: An Overview (2017, background): “search for objects sequentially, considering both the current observation and previous search paths, by maximizing the long-term reward associated with localization accuracy over all objects with DQN.Mathe et al. (2016) proposed to use policy search for visual object detection.Kong et al.(2017) depl”
Multi-Scale Deep Reinforcement Learning for Real-Time 3D-Landmark Detection in CT Scans (2019, background): “stochastic policies for how and where to apply detectors for object localization [61].”
Learning to Look Around: Intelligently Exploring Unseen Environments for Unknown Tasks (2017, background): “While there is interesting recent headway in active object recognition [3, 11, 29, 43] and intelligent search mechanisms for detection [10, 32, 45, 73], such systems are supervised and task-specific—limited to accelerating a predefined recognition task.”
Reinforced Attention for Few-Shot Learning and Beyond (2021, background): “The applications are also studied on more classic tasks, such as classification [61], object detection [2, 35], segmentation [1, 66] and pose estimation [24, 44].”