Thread by @ai_fast_track

✨Common Object Detector Architecture you should be familiar with:

📌 Common object detectors are divided into One-Stage Detectors (OSD), and Two-Stage Detectors (TSD)

📌 Both OSD and TSD can be either anchor-based (relying on anchor boxes) or anchor-free

📌 OSD use the whole feature maps to predict bounding boxes/labels: Dense Prediction

📌 TSD have an extra step hence two-stage: extracting proposals (regions of interest)

📌 Proposals are used to extract feature map regions to predict bounding boxes/labels: Sparse Prediction

📌 TSD don't use the whole feature map for prediction

📌 TSD (e.g. Faster R-CNN) used to be more accurate than STD (e.g. SSD, YOLO, etc.)

📌 STD (e.g. EfficientDet, RetinaNet, VFNet, YOLOX, etc.) recently show better results than TSD

📌 STD are faster than TSD

🔥IceVision supports most of the models shown in the figure.

Come and join our friendly/helpful community!

⌨IceVision: github.com/airctic/IceVis…
🍕Forum: discord.gg/JDBeZYK

Thanks for passing by!

🟧 Def Follow @ai_fast_track for more stuff on Object Detection

🟦 and if you could give the thread a quick retweet, it will help other people catch this content in their feed 🙏

https://twitter.com/ai_fast_track/status/1453368771285032971