YOLOv3: An Incremental Improvement

by   Joseph Redmon, et al.

We present some updates to YOLO! We made a bunch of little design changes to make it better. We also trained this new network that's pretty swell. It's a little bigger than last time but more accurate. It's still fast though, don't worry. At 320x320 YOLOv3 runs in 22 ms at 28.2 mAP, as accurate as SSD but three times faster. When we look at the old .5 IOU mAP detection metric YOLOv3 is quite good. It achieves 57.9 mAP@50 in 51 ms on a Titan X, compared to 57.5 mAP@50 in 198 ms by RetinaNet, similar performance but 3.8x faster. As always, all the code is online at https://pjreddie.com/yolo/



page 6


Faster ILOD: Incremental Learning for Object Detectors based on Faster RCNN

The human vision and perception system is inherently incremental where n...

VSAC: Efficient and Accurate Estimator for H and F

We present VSAC, a RANSAC-type robust estimator with a number of novelti...

Mining Minimal Map-Segments for Visual Place Classifiers

In visual place recognition (VPR), map segmentation (MS) is a preprocess...

The Cardan grille approach to the Voynich MS taken to the next level

The Voynich MS is an illustrated 15th century manuscript, whose text is ...

Deuteros 2.0: Peptide-level significance testing of data from hydrogen deuterium exchange mass spectrometry

Summary: Hydrogen deuterium exchange mass spectrometry (HDX-MS) is becom...

Impact of URI Canonicalization on Memento Count

Quantifying the captures of a URI over time is useful for researchers to...

Code Repositories


Latest Data Science Materials

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.