YOLOX is an anchor-free version of YOLO, with a simpler design but better performance! It aims to bridge the gap between research and industrial communities. This note reviews YOLOX and an experiment on our custom traffic sign dataset for VIA Project

A review of YOLOX, the anchor-free YOLO with a decoupled head and SimOTA, plus a hands-on traffic-sign detection experiment on the VIA dataset.

Paper review: "YOLOX: Exceeding YOLO Series in 2021" and application in traffic sign detection - VIA Autonomous

This is my note for 3 papers: CenterTrack - 2D object tracking, CenterPoint - 3D object detection and tracking, and CenterPoint++ - submission to the Waymo Real-time 3D Detection Challenge

Reading notes on three papers: CenterTrack for 2D tracking, CenterPoint for 3D detection and tracking, and CenterPoint++ for the Waymo real-time challenge.

Paper review: CenterTrack - CenterPoint - CenterPoint++

LiDAR-based or RGB-D-based object detection is used in numerous applications, ranging from autonomous driving to robot vision. In this note, we review about SECOND: Sparsely Embedded Convolutional Detection, a SOTA 3D object detection network in 2018. This note only sums up the main points of the paper.

A paper review of SECOND, the sparse-convolution 3D LiDAR detector: its GPU rule generation, angle loss, and point-cloud data augmentation.

Lidar

Paper review: "YOLOX: Exceeding YOLO Series in 2021" and application in traffic sign detection - VIA Autonomous

Paper review: CenterTrack - CenterPoint - CenterPoint++

Paper review: SECOND - Sparsely Embedded Convolutional Detection