Saved in:
Bibliographic Details
Main Author: Sun, Liang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.28050
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911552983007232
author Sun, Liang
author_facet Sun, Liang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_28050
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Object Detection Based on Distributed Convolutional Neural Networks
Sun, Liang
Computer Vision and Pattern Recognition
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.
title Object Detection Based on Distributed Convolutional Neural Networks
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.28050