Why Is SSD Faster Than YOLO v1 and More Accurate than Faster R-CNN? — In 2015, Wei Liu et al. published a paper on SSD (Single Shot MultiBox Detector). It was faster than YOLO v1 (the first version) and more accurate than Faster R-CNN. This article explains what made SSD so good. 1. Background 1.1. Motivation The first author Wei Liu was a University of North Carolina student…

You Look Only Once (The 1st Version) — YOLO is an object detection model that is very fast, pretty accurate, yet simple. This article explains the architecture of YOLO (the 1st version). 1. Background In 2015, Joseph Redmon (University of Washington) developed YOLO. One of his co-authors, Ross Girshick (Microsoft Research), published a paper for Faster R-CNN around the same…

Real-Time Object Detection with RPN — There was no doubt Fast R-CNN was faster than R-CNN. What used to take 47 seconds per image went down to 0.22 seconds. That is, Fast R-CNN was 213 times faster than R-CNN. It significantly improved inference speed, albeit excluding the region proposal step that took around 2 seconds. It…

Understanding why it’s 213 Times Faster than R-CNN and More Accurate — In 2013, Ross Girshick et al. introduced R-CNN, an object detection model that combines convolutional layers with existing computer vision techniques, breaking previous records. It was a groundbreaking model at the time. In 2015, Ross Girshick developed Fast R-CNN, setting a new record. It was more accurate, and the inference…

R-CNN = CNN Extracting Features + SVM Classifier — R-CNN (Region-based Convolutional Neural Network) was an epoch-making model in 2013 which successfully combined CNN with classical computer vision techniques for object detection and broke the previous record. …

Understanding the Logic and Tricky Part of NMS Object detection models like YOLOv5 and SSD predict objects’ locations by generating bounding boxes (shown in blue rectangles below). However, object detection models produce more bounding boxes than the final output with different locations, sizes, and confidence levels. They do not just…

Calculating mean Average Precision (mAP) with Confidence — We use mean Average Precision (mAP) when evaluating object detection models like YOLO and SSD. This article explains the objective of mAP and how to calculate it. In object detection, a model predicts the locations of objects and their classes (i.e., dog, cat, human, vehicle, etc.), where we need to…

Understanding Intuition and Calculation — The previous article discussed the difference between object detection and image classification. There we briefly mentioned Intersection over Union (IoU). This article explains more details on IoU and how to calculate it. 1. Intersection over Union — Intuition The below image shows a ground truth bounding box (red color) for a dog.

Understanding the Simple Difference — This article explains the difference between object detection vs image classification (i.e., ResNet). 1. Image Classification The objective of Image Classification is to answer what object exists in an image. For example, what is a representative object in the below image?