🥇YOLOX beat YOLOv5. They won the 1st Place on Streaming Perception Challenge (Workshop on Autonomous Driving at CVPR 2021).
I briefly explain how they created it, here below👇
YOLOX will be soon supported in our IceVision Framework (Repo: github.com/airctic/IceVis…)
I briefly explain how they created it, here below👇
YOLOX will be soon supported in our IceVision Framework (Repo: github.com/airctic/IceVis…)
Considering YOLOv4 and YOLOv5 might be a little bit over-optimized for the anchor-based pipeline, they choose YOLOv3 as their starting point.
They transformed YOLOv3 into YOLOX by using the following techniques:
🟦 Decoupled head,
🟦 Anchor-free architecture (like FCOS), and
They transformed YOLOv3 into YOLOX by using the following techniques:
🟦 Decoupled head,
🟦 Anchor-free architecture (like FCOS), and
🟦 Advanced label assigning strategy (SimOTA)
They also used some other training strategies such as: adding EMA weights updating, cosine LR schedule, IoU loss, and IoU-aware branch.
pdf: arxiv.org/pdf/2107.08430…
abs: arxiv.org/abs/2107.08430
repo: github.com/Megvii-BaseDet…
They also used some other training strategies such as: adding EMA weights updating, cosine LR schedule, IoU loss, and IoU-aware branch.
pdf: arxiv.org/pdf/2107.08430…
abs: arxiv.org/abs/2107.08430
repo: github.com/Megvii-BaseDet…
Thanks for passing by!
🟧 Definitely Follow @ai_fast_track for more stuff on Object Detection
🟦 Retweet the first tweet to help other discover this content
🟧 Definitely Follow @ai_fast_track for more stuff on Object Detection
🟦 Retweet the first tweet to help other discover this content
https://twitter.com/ai_fast_track/status/1451211938529165312
• • •
Missing some Tweet in this thread? You can try to
force a refresh
