HackerPapers

arXiv:1804.02767cs.CV

YOLOv3: An Incremental Improvement

Joseph Redmon, Ali Farhadi

Abstract

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/

arXiv comments
Tech Report
Journal reference
DOI
Subjects
cs.CVComputer Vision and Pattern Recognition

On Hacker News

Linked by 4 identifiable commenters in 4 comments across 4 threads, from Jan 2019 to Nov 2022. Found in 1 HN submission from May 2020 to May 2020. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments4 threads

    • YOLO v3's paper is hilarious. The model was state of the art at the time, yet it's written in a tongue-in-cheek way: https://arxiv.org/pdf/1804.02767.pdf

      derekpankaewView on HNParent context

  1. My Favourite Git Commit 1 comment
    • My favorite (in terms of dark humor, if we’re honest) is YOLO, one of the more interesting deep learning object detectors. [1] It is the exact opposite of yours in every way. The code is brilliant however. Even the papers are snarky. [2] [1]…

      mikehollingerView on HNParent context

    • When I see a title with possibly overblown philosophical implications, I get cautious. When I see "Max Tegmark", it is a sign to close a tab. While science, in general, suffers from overblowing implications (as in promising that given research revolutionizes everything, etc - to…

      staredView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.