R-CNN Explained

This is a R CNN tutorial video in which I dive deep into what is R CNN and r cnn basics.
This video is a part of object detection series and the first one in that is RCNN for object detection.
By the end of this video you would be able to understand the R CNN algorithm in detail to understand clearly as to how rcnn works . We start with what selective search is and how rcnn uses selective search to get region proposals . We then move on to the different stages of training RCNN, RCNN architecture, talk about bounding box regressors in R-CNN and lastly discuss the results RCNN gets on object detection task. By the end of this video you should be able to understand all parts of object detection using rcnn .
📖 Resources
RCNN Paper - tinyurl.com/exai-rcnn-paper
Graph Segmentation - tinyurl.com/exai-rcnn-graph-p...
Selective Search - tinyurl.com/exai-rcnn-ss-paper
Selective Search opencv implementation - tinyurl.com/exai-rcnn-ss-open...
⏱️ Timestamps
00:00 Introduction
00:30 Classification vs Localization vs Detection
03:40 Object Detection using Sliding Window Approach
06:17 Object detection using RCNN - Introduction
08:11 Selective Search in RCNN for region proposals
13:50 RCNN : Supervised Pre-training and Finetuning
19:12 RCNN : SVM Training
22:20 Why use SVM in R-CNN
26:00 Bounding Box Regression Training in RCNN
28:42 Non-Maximum Suppression | NMS in Object Detection
31:14 RCNN Results
33:18 Outro
🔔 Subscribe :
tinyurl.com/exai-channel-link
Background Track - Fruits of Life by Jimena Contreras
Email - [e-mail]
📌 Keywords:
#objectdetection

[@sladewinter]

Thank you very much for this series, and the overall amazing content, genuinely appreciated !

[@Explaining-AI]

Thank you so much for this comment :)

[@ArpitAnand-yd7tr]

Great video as always. Appreciate the way you logically break down the reasons for architectural choices and smoothly transition to successive steps
Eagerly waiting for the next video in the series!
Just wondering if you intend to cover MobileNetV2 and EfficientNetV2 in this series

[@Explaining-AI]

Thank you so much for that! Actually those two wont be covered in this. I plan to do a separate one on popular backbone architectures like vgg/inception/resnet/mobilenet/efficientnet/darknet/swin e.t.c so I will cover them in that series.

[@wolfpack7330]

Very well done

[@Explaining-AI]

Thank You!

[@khadimhussain6155]

can you also explain pytorch code for RCNN

[@Explaining-AI]

Hello, I will soon be doing a video on implementation of faster rcnn, in which I will cover the PyTorch code as well.

[@yuuno__]

will you cover MAMBA implementation later? I think there's no current video with clear explanation. It would be very nice if you do it.

[@Explaining-AI]

Hello,
I indeed plan to cover it but it wont be part of this series.
I have 3-4 topics that I intend to cover first and then after that will do a video on Mamba.

[@goneshivachandhra7470]

Is detr covered in this series

[@Explaining-AI]

yes it would cover DETR as well. After FasterRCNN, I plan to do Yolo/SSD/FPN and then I will get into DETR.