You Only Look Once: Unified, Real-Time Object Detection

TL;DR

YOLO introduces a unified, real-time object detection system that predicts bounding boxes and class probabilities directly from images, achieving high speed and accuracy, and demonstrating strong generalization across different image domains.

Contribution

This paper presents YOLO, a novel single neural network framework for real-time object detection that outperforms previous methods in speed and generalization capabilities.

Findings

Processes images at 45 fps with the base model.

Fast YOLO achieves 155 fps with double the accuracy of other real-time detectors.

Outperforms previous methods on generalization to artwork datasets.

Abstract

We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities. A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation. Since the whole detection pipeline is a single network, it can be optimized end-to-end directly on detection performance. Our unified architecture is extremely fast. Our base YOLO model processes images in real-time at 45 frames per second. A smaller version of the network, Fast YOLO, processes an astounding 155 frames per second while still achieving double the mAP of other real-time detectors. Compared to state-of-the-art detection systems, YOLO makes more localization errors but is far less likely to predict false detections where nothing exists. Finally, YOLO learns very general representations of objects. It outperforms all other detection methods, including DPM and R-CNN, by a wide margin when generalizing from natural images to artwork on both the Picasso Dataset and the People-Art Dataset.