Classification of Occluded Objects using Fast Recurrent Processing

05/06/2015
by   Özgür Yılmaz, et al.
0

Recurrent neural networks are powerful tools for handling incomplete data problems in computer vision, thanks to their significant generative capabilities. However, the computational demand for these algorithms is too high to work in real time, without specialized hardware or software solutions. In this paper, we propose a framework for augmenting recurrent processing capabilities into a feedforward network without sacrificing much from computational efficiency. We assume a mixture model and generate samples of the last hidden layer according to the class decisions of the output layer, modify the hidden layer activity using the samples, and propagate to lower layers. For visual occlusion problem, the iterative procedure emulates feedforward-feedback loop, filling-in the missing hidden layer activity with meaningful representations. The proposed algorithm is tested on a widely used dataset, and shown to achieve 2× improvement in classification accuracy for occluded objects. When compared to Restricted Boltzmann Machines, our algorithm shows superior performance for occluded object classification.

READ FULL TEXT

page 2

page 9

research
04/21/2021

Recurrent Feedback Improves Recognition of Partially Occluded Objects

Recurrent connectivity in the visual cortex is believed to aid object re...
research
09/12/2019

Recurrent Connectivity Aids Recognition of Partly Occluded Objects

Feedforward convolutional neural networks are the prevalent model of cor...
research
05/28/2019

Compositional Convolutional Networks For Robust Object Classification under Occlusion

Deep convolutional neural networks (DCNNs) are powerful models that yiel...
research
12/22/2019

Recurrent Feedback Improves Feedforward Representations in Deep Neural Networks

The abundant recurrent horizontal and feedback connections in the primat...
research
07/20/2019

Recurrent Connections Aid Occluded Object Recognition by Discounting Occluders

Recurrent connections in the visual cortex are thought to aid object rec...
research
03/26/2020

Going in circles is the way forward: the role of recurrence in visual inference

Biological visual systems exhibit abundant recurrent connectivity. State...
research
06/06/2016

Feedforward Initialization for Fast Inference of Deep Generative Networks is biologically plausible

We consider deep multi-layered generative models such as Boltzmann machi...

Please sign up or login with your details

Forgot password? Click here to reset