Hierarchical Object Detection with Deep Reinforcement Learning

By Miriam Bellver, Xavier Giró-i-Nieto, Ferran Marqués, Jordi Torres. 2016

115 citations recorded by the source corpus.

We present a method for performing hierarchical object detection in images guided by a deep reinforcement learning agent. The key idea is to focus on those parts of the image that contain richer information and zoom on them. We train an intelligent agent that, given an image window, is capable of deciding where to focus the attention among five different predefined region candidates (smaller windows). This procedure is iterated providing a hierarchical image analysis. We compare two different candidate proposal strategies to guide the object search: with and without overlap. Moreover, our work compares two different strategies to extract features from a convolutional neural network for each region proposal: a first one that computes new feature maps for each region proposal, and a second one that computes the feature maps for the whole image to later generate crops for each region proposal. Experiments indicate better results for the overlapping candidate proposal strategy and a loss of performance for the cropped image features due to the loss of spatial resolution. We argue that, while this loss seems unavoidable when working with large amounts of object candidates, the much more reduced amount of region proposals generated by our reinforcement learning agent allows considering to extract features for each location without sharing convolutional computation among regions.

Subfields: 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 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].”
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”