Object Detection Part 5: You Only Look Once (YOLO), YOLOv1 Architecture

This is the fifth video in the object detection series where we explore the You Only Look Once (YOLO) architecture and what improvements it brings in comparison with the RCNN family of models. In short, as the name suggests, the YOLO model performs object detection in a single step compared to RCNN which performs object detection in two steps.

*References*
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
"You Only Look Once: Unified, Real-Time Object Detection" paper: https://arxiv.org/abs/1506.02640

*Related Videos*
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
R-CNN, Sliding Window and Selective Search: https://youtu.be/26PWiWCz1v8
Fast R-CNN, Region Projection and Region of Interest (RoI) Pooling Layer: https://youtu.be/mOi5VDRLVH0
Faster R-CNN, Region Proposal Network and Intersection over Union: https://youtu.be/68VE1gebfVc
Mask RCNN, Mask Prediction Branch and Region of Interest Align (ROIAlign): https://youtu.be/jvLaKF0LSCY
The Hungarian Matching: https://youtu.be/oo-H_ZY2TGA
Why Neural Networks Can Learn Any Function: https://youtu.be/O45AaRPQhuI
Why Deep Neural Networks (DNNs) Underperform Tree-Based Models on Tabular Data: https://youtu.be/e62CBva4TYc
Why Residual Connections (ResNet) Work: https://youtu.be/Gey9CG6R6w8

*Contents*
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
00:00 - Intro
00:37 - RCNN Issues
01:10 - YOLO Architecture
02:17 - Anchor Matching
03:23 - Inference
03:49 - YOLO Drawbacks
04:30 - Outro

*Follow Me*
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
🐦 Twitter: @datamlistic https://twitter.com/datamlistic
📸 Instagram: @datamlistic https://www.instagram.com/datamlistic
📱 TikTok: @datamlistic https://www.tiktok.com/@datamlistic

*Channel Support*
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
The best way to support the channel is to share the content. ;)

If you'd like to also support the channel financially, donating the price of a coffee is always warmly welcomed! (completely optional and voluntary)
► Patreon: https://www.patreon.com/datamlistic
► Bitcoin (BTC): 3C6Pkzyb5CjAUYrJxmpCaaNPVRgRVxxyTq
► Ethereum (ETH): 0x9Ac4eB94386C3e02b96599C05B7a8C71773c9281
► Cardano (ADA): addr1v95rfxlslfzkvd8sr3exkh7st4qmgj4ywf5zcaxgqgdyunsj5juw5
► Tether (USDT): 0xeC261d9b2EE4B6997a6a424067af165BAA4afE1a

#yolo #objectdetection #computervision

Тэги:

#deep_learning #machine_learning #artificial_intelligence #ml #dl #ai #data_science #ds #why_ml #why_dl #yolo #you_only_look_once #object_detection #computer_vision #rcnn #fast_rcnn #faster_rcnn #yolo_explained #yolo_model #you_only_look_once_model

Скачать видео