Baoliang CHEN(陈宝亮)'s repositories
IACA_For_Lowlight_IQA
Code for "Gap-closing Matters: Perceptual Quality Evaluation and Optimization of Low-Light Image Enhancement"
BIQA_Tools_For_CustomDataset
Test BIQA methods on my own dataset
awesome-segment-anything
Tracking and collecting papers/projects/others related to Segment Anything.
Baoliang93.github.io
AcadHomepage: A Modern and Responsive Academic Personal Homepage
BERT-whitening
简单的向量白化改善句向量质量
Dassl.pytorch
A PyTorch toolbox for domain adaptation and semi-supervised learning.
deepiqa
Potential of deep features for opinion-unaware, distortion-unaware, no-reference image quality assessment
Transfer-Learning-Library
Transfer Learning Library for Domain Adaptation and Finetune.
Generalization-Causality
一些domain generalization相关的阅读笔记
Image-Quality-Assessment
IQA( FID, PSNR, FSIM, SSIM, MAE & FPM) indicator test code
Image-Quality-Assessment-By-Multiple-Models
Using multiple models (CNN, LeNet-5, ResNet, VGG) to implement IQA and compare their performance
MedSAM
The official repository for MedSAM: Segment Anything in Medical Images.
NTIRE2021-IQA-MACS
NTIRE 2021, Image Quality Assessment Challenge (MACS team)
Pre-Trained-Language-Models-for-Interactive-Decision-Making
Pre-Trained Language Models for Interactive Decision-Making [NeurIPS 2022]
pytorch-loss-functions
A collection of loss functions with easy usage
Q-Bench
A benchmark for multi-modality LLMs (MLLMs) on low-level vision and visual quality assessment.
Sed-Awesome-Segment-Anything
This repository is for the first comprehensive survey on Meta AI's Segment Anything Model (SAM).
Train_Custom_Dataset
标注自己的数据集,训练、评估、测试、部署自己的人工智能算法
transferlearning
Everything about Transfer Learning and Domain Adaptation--迁移学习
TReS
No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistency
UEGAN
[TIP2020] Pytorch implementation of "Towards Unsupervised Deep Image Enhancement with Generative Adversarial Network"
UMNN
Implementation of Unconstrained Monotonic Neural Network and the related experiments. These architectures are particularly useful for modelling monotonic transformations in normalizing flows.
visual-mic
Passive Recovery of Sound from Video