This is the second video in the object detection series and in it we are exploring how the Fast R-CNN model improves the R-CNN model by projecting the proposed regions into the feature map and by using the region of interest (RoI) pooling layer.

*References*
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks" paper: [ Ссылка ]
"Selective Search for Object Recognition" paper: [ Ссылка ]
Selective search explained: [ Ссылка ]

*Related Videos*
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
Object Detection Part 1: R-CNN, Sliding Window and Selective Search: [ Ссылка ]
Object Detection Part 3: Faster R-CNN, Region Proposal Network and Intersection over Union: [ Ссылка ]
Why Neural Networks Can Learn Any Function: [ Ссылка ]
Why Deep Neural Networks (DNNs) Underperform Tree-Based Models on Tabular Data: [ Ссылка ]
Why Residual Connections (ResNet) Work: [ Ссылка ]

*Contents*
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
00:00 - Intro
00:22 - R-CNN Recap
00:49 - Faster R-CNN Model
01:25 - Region Projection
02:19 - Region of Interest (RoI) Pooling
02:49 - Fast R-CNN Issues
03:22 - Outro

*Follow Me*
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
🐦 Twitter: @datamlistic [ Ссылка ]
📸 Instagram: @datamlistic [ Ссылка ]
📱 TikTok: @datamlistic [ Ссылка ]

*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: [ Ссылка ]
► Bitcoin (BTC): 3C6Pkzyb5CjAUYrJxmpCaaNPVRgRVxxyTq
► Ethereum (ETH): 0x9Ac4eB94386C3e02b96599C05B7a8C71773c9281
► Cardano (ADA): addr1v95rfxlslfzkvd8sr3exkh7st4qmgj4ywf5zcaxgqgdyunsj5juw5
► Tether (USDT): 0xeC261d9b2EE4B6997a6a424067af165BAA4afE1a

#cnn #rcnn #fastrcnn #objectdetection #roipooling

свернуть