Object Detection Based on Distributed Convolutional Neural Networks

TL;DR

This paper introduces a simple object detection method using Distributed Convolutional Neural Networks that detects objects by identifying high-scoring patches across scales and forming bounding boxes.

Contribution

It proposes a novel detection approach based on DisCNN modules' monotonicity and parallel processing, improving speed and simplicity over traditional methods.

Findings

Detection by overlapping high-scoring patches across scales.

Requires only object-centered images with class labels for training.

Parallel detection for multiple classes accelerates the process.

Abstract

Based on the Distributed Convolutional Neural Network(DisCNN), a straightforward object detection method is proposed. The modules of the output vector of a DisCNN with respect to a specific positive class are positively monotonic with the presence probabilities of the positive features. So, by identifying all high-scoring patches across all possible scales, the positive object can be detected by overlapping them to form a bounding box. The essential idea is that the object is detected by detecting its features on multiple scales, ranging from specific sub-features to abstract features composed of these sub-features. Training DisCNN requires only object-centered image data with positive and negative class labels. The detection process for multiple positive classes can be conducted in parallel to significantly accelerate it, and also faster for single-object detection because of its lightweight model architecture.