Foundation models based medical image analysis

solo-learn: a library of self-supervised methods for visual representation learning powered by Pytorch Lightning

OpenMMLab Pre-training Toolbox and Benchmark

Compute the mean absolute error (MAE) incrementally.

Compute a moving mean absolute error (MAE) incrementally.

SimpleAICV:pytorch training and testing examples.

[ECCV 2024] Improving 2D Feature Representations by 3D-Aware Fine-Tuning

tool for compare and adjust images

[SHREC24] Skeleton-based Self-Supervised Learning For Dynamic Hand Gesture Recognition

資料科學的日常研究議題

[Survey] Masked Modeling for Self-supervised Representation Learning on Vision and Beyond (https://arxiv.org/abs/2401.00897)

Develop a deep learning model capable of predicting traffic flow in urban environments. The model will utilize historical traffic data, weather conditions, and road configurations to forecast traffic patterns. This information can be invaluable for traffic management systems, helping to optimize traffic signals and reduce congestion, ultimately.

PySODEvalToolkit: A Python-based Evaluation Toolbox for Salient Object Detection and Camouflaged Object Detection

Efficient Network Traffic Classification via Pre-training Unidirectional Mamba

Artificial intelligence (AI, ML, DL) performance metrics implemented in Python

Book Recommendation System

[ICML 2023] Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN

Adversarial Patch defense using SegmentAndComplete (SAC) & Masked AutoEncoder (MAE)

Linear regression models are used to predict football player attacking stats based on attributes like finishing and passing, with the model trained, evaluated, and applied for predictions. Multiple features improve accuracy, and performance is assessed using metrics like MSE and R-squared.