Wong Yi Jie's Projects
We design a multi-task model for joint disaster classification and victim detection. We train the model using both the Centralized Learning (CL) and Federated Learning (FL) methods. We also tried Active Learning (AL) to see how it could help in reducing the labeling workload for disaster dataset. Lastly, we optimized the model using OpenVINO.
A project demonstrating how to use CUDA-PointPillars to deal with cloud points data from lidar.
Convolutional Neural Networks
Efficient YOLOv8 inference depends not only on GPU specifications but also on CPU processing. However, the significance of fully utilizing the CPU is often overlooked. In this repository, we explore how to utilize CPU multi-threading to enhance inference speed.
Team: Double Y
To train a fingerprint verification encoder via Siamese/Triplet network.
Most tutorials on GradCAM are made for Image Classification tasks. This repo will provide an example of GradCAM for object detection using YOLOv3.
Fast kitti object detection eval in python(finish eval in less than 10 second)
A lightweight tool for labeling 3D bounding boxes in point clouds.
Shadow Removal by a Lightness-Guided Network with Training on Unpaired Data
Train a lightweight MobileNetV2 model for disaster classification using the Crisis Image Benchmark Datasets (CrisisIBD).
OpenCV AI Competition 2021
OpenPCDet Toolbox for LiDAR-based 3D Object Detection.
Face Recognition on SurvFace or Custom Dataset using OpenSphere
Multi Camera Face Detection and Recognition with Tracking
Find pre-installed Open3D package in CMake
Representation Similarity Analysis (RSA) to measure the similarity of the feature maps extracted by two models.
SuperYOLO is accepted by TGRS
IEEE WCNC 2023: Deep Reinforcement Learning for Secrecy Energy-Efficient UAV Communication with Reconfigurable Intelligent Surfaces
To train a walkable path road segmentation model for a pedestrian's perspective
YoloV3 Implemented in Tensorflow 2.0