Deep Active Object Recognition by Joint Label and Action Prediction

by   Mohsen Malmir, et al.

An active object recognition system has the advantage of being able to act in the environment to capture images that are more suited for training and that lead to better performance at test time. In this paper, we propose a deep convolutional neural network for active object recognition that simultaneously predicts the object label, and selects the next action to perform on the object with the aim of improving recognition performance. We treat active object recognition as a reinforcement learning problem and derive the cost function to train the network for joint prediction of the object label and the action. A generative model of object similarities based on the Dirichlet distribution is proposed and embedded in the network for encoding the state of the system. The training is carried out by simultaneously minimizing the label and action prediction errors using gradient descent. We empirically show that the proposed network is able to predict both the object label and the actions on GERMS, a dataset for active object recognition. We compare the test label prediction accuracy of the proposed model with Dirichlet and Naive Bayes state encoding. The results of experiments suggest that the proposed model equipped with Dirichlet state encoding is superior in performance, and selects images that lead to better training and higher accuracy of label prediction at test time.


page 6

page 19


Belief Tree Search for Active Object Recognition

Active Object Recognition (AOR) has been approached as an unsupervised l...

Adaptive Object Detection with Dual Multi-Label Prediction

In this paper, we propose a novel end-to-end unsupervised deep domain ad...

Hyper-parameter optimization of Deep Convolutional Networks for object recognition

Recently sequential model based optimization (SMBO) has emerged as a pro...

Deep Reinforcement Learning Models Predict Visual Responses in the Brain: A Preliminary Result

Supervised deep convolutional neural networks (DCNNs) are currently one ...

Generative Model with Coordinate Metric Learning for Object Recognition Based on 3D Models

Given large amount of real photos for training, Convolutional neural net...

Optimistic and Pessimistic Neural Networks for Scene and Object Recognition

In this paper the application of uncertainty modeling to convolutional n...

Seeing by haptic glance: reinforcement learning-based 3D object Recognition

Human is able to conduct 3D recognition by a limited number of haptic co...

Please sign up or login with your details

Forgot password? Click here to reset