Recurrent Connectivity Aids Recognition of Partly Occluded Objects

09/12/2019
by   Markus Roland Ernst, et al.
9

Feedforward convolutional neural networks are the prevalent model of core object recognition. For challenging conditions, such as occlusion, neuroscientists believe that the recurrent connectivity in the visual cortex aids object recognition. In this work we investigate if and how artificial neural networks can also benefit from recurrent connectivity. For this we systematically compare architectures comprised of bottom-up (B), lateral (L) and top-down (T) connections. To evaluate performance, we introduce two novel stereoscopic occluded object datasets, which bridge the gap from classifying digits to recognizing 3D objects. The task consists of recognizing one target object occluded by multiple occluder objects. We find that recurrent models perform significantly better than their feedforward counterparts, which were matched in parametric complexity. We show that for challenging stimuli, the recurrent feedback is able to correctly revise the initial feedforward guess of the network. Overall, our results suggest that both artificial and biological neural networks can exploit recurrence for improved object recognition.

READ FULL TEXT

page 1

page 2

page 3

page 5

page 6

page 7

page 8

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
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
03/25/2019

The functional role of cue-driven feature-based feedback in object recognition

Visual object recognition is not a trivial task, especially when the obj...
research
02/13/2019

Which Neural Network Architecture matches Human Behavior in Artificial Grammar Learning?

In recent years artificial neural networks achieved performance close to...
research
05/22/2017

Learning Robust Object Recognition Using Composed Scenes from Generative Models

Recurrent feedback connections in the mammalian visual system have been ...
research
10/11/2021

Recurrent Attention Models with Object-centric Capsule Representation for Multi-object Recognition

The visual system processes a scene using a sequence of selective glimps...
research
05/06/2015

Classification of Occluded Objects using Fast Recurrent Processing

Recurrent neural networks are powerful tools for handling incomplete dat...

Please sign up or login with your details

Forgot password? Click here to reset