Skip to content
The methodOpen data
Back to the collection

YOLOv3: An Incremental Improvement

Joseph Redmon, Ali Farhadi

2018 · arXiv

Other research
Read the paper
HN score
0
Mentions
3
Readers
3
Months
3
What’s in a score?

From the 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/

Metadata: arXiv. Abstracts retain their original authors’ rights.

In the conversation

Original HN comments, with labels from simple text rules. A label describes the whole comment and may miss context or irony. Read the discussion to make up your own mind. About the labels

3 selected excerpts · 3 total mentions

mikehollinger
Neutral mention · rule
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] https://github.com/pjreddie/darknet/commits/master [2] https://arxiv.org/pdf/1804.02767.pdf
Original comment My Favourite Git Commit
stared
Neutral mention · rule
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 get credit and the next grant), he is an ace of that. To contrast it with "YOLOv3: An Incremental Improvement" https://arxiv.org/abs/1804.02767 in which the author goes to the other extreme, being bluntly honest.
Original comment Consciousness as a State of Matter (2015)

Keep following the thread.

More in Other research

More from the same topics.