Comparative study of Object Detection

This is comprehensive journey on object detection. I have followed the original research paper published on these particular topics.
Region based object detectors
In region based object detection I have studied about different models / algorithms from research paper on these topics. Here is the some research papers that I have followed and the links and description are given below.
1. R-CNN: Regions with CNN features | Source: Rich feature hierarchies for accurate object detection and semantic segmentation
2. Fast R-CNN: Fast Regions with CNN features | Source: Fast R-CNN
3. Faster R-CNN: Faster Regions with CNN features | Source: Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
4. R-FCN: Region-based Fully Convolutional Networks | Source: R-FCN: Object Detection via Region-based Fully Convolutional Networks

---

Single shot object detectors
In single shot based object detection I have studied about different models / algorithms from research paper on these topics. Here is the some research papers that I have followed and the links and description are given below.
1. SSD: Single Shot MultiBox Detector | Source: SSD: Single Shot MultiBox Detector
2. YOLO: You Only Look Once | Source: You Only Look Once: Unified, Real-Time Object Detection
3. YOLO-v2: YOLO9000: Better, Faster, Stronger | Source: YOLO9000: Better, Faster, Stronger
4. YOLO-v3: YOLOv3: An Incremental Improvement | Source: YOLOv3: An Incremental Improvement

---

Other object detection models
1. FPN: Feature Pyramid Networks for Object Detection | Source: Feature Pyramid Networks for Object Detection
2. FPN with Faster R-CNN: An Anchor-Free Region Proposal Network for Faster R-CNN based Text Detection Approaches | Source: An Anchor-Free Region Proposal Network for Faster R-CNN based Text Detection Approaches
3. Focal loss (RetinaNet): Focal Loss for Dense Object Detection| Source: Focal Loss for Dense Object Detection

---