SPARCNN: SPAtially Related Convolutional Neural Networks

TL;DR

SPARCNN enhances object detection accuracy by leveraging spatial relationships between objects, significantly improving performance in cluttered scenes compared to traditional CNN approaches.

Contribution

This paper introduces SPARCNN, a novel method that incorporates probabilistic spatial relationships into CNN-based detection, addressing limitations in cluttered multi-object scenarios.

Findings

Increases classification accuracy by 8% over non-spatial methods.

Achieves an 18.8% boost in performance with highly obscured objects.

Effective in cluttered and complex scenes.

Abstract

The ability to accurately detect and classify objects at varying pixel sizes in cluttered scenes is crucial to many Navy applications. However, detection performance of existing state-of the-art approaches such as convolutional neural networks (CNNs) degrade and suffer when applied to such cluttered and multi-object detection tasks. We conjecture that spatial relationships between objects in an image could be exploited to significantly improve detection accuracy, an approach that had not yet been considered by any existing techniques (to the best of our knowledge) at the time the research was conducted. We introduce a detection and classification technique called Spatially Related Detection with Convolutional Neural Networks (SPARCNN) that learns and exploits a probabilistic representation of inter-object spatial configurations within images from training sets for more effective region proposals to use with state-of-the-art CNNs. Our empirical evaluation of SPARCNN on the VOC 2007 dataset shows that it increases classification accuracy by 8% when compared to a region proposal technique that does not exploit spatial relations. More importantly, we obtained a higher performance boost of 18.8% when task difficulty in the test set is increased by including highly obscured objects and increased image clutter.