Name: Qi BI
Type: User
Company: University of Amsterdam
Bio: UvAer WHUer
image understanding;
machine learning and pattern recognition;
aerial image processing
Location: Computer Vision Group, Insititute of Informatics, University of Amsterdam, Netherland
Blog: https://scholar.google.com/citations?user=v6RAqYwAAAAJ&hl=zh-CN
Qi BI's Projects
Single-Stage Semantic Segmentation from Image Labels (CVPR 2020)
[CVPR 2020] Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuning
Official implementation of paper "Learning Attraction Field Map for Robust Line Segment Detection" (CVPR 2019)
The model of "Attention Based Glaucoma Detection: A Large-scale Database with a CNN Model" (CVPR2019)
Source code of our AGOS framework, submitted to TGRS 2022
AlexNet for Tiangong Data Competition held by Baidu
All-day Semantic Segmentation & All-day CityScapes dataset
Spatial/Channel-spatial attention based multi-instance CNN for classification
Awesome Multi-label Image Recognition Paper List
A curated list of awesome neural radiance fields papers
A curated list of awesome self-supervised methods
:metal: awesome-semantic-segmentation
My webpage
General Multi-label Image Classification with Transformers
official implementation of the proposed Content-enhanced Mask2Former for domain generalized urban-scene semantic segmentation
Convolutional Oriented Boundaries
Demo for MSCP which will be appeared on TGRS
Implementation for NeurIPS oral paper: Causal Intervention for Weakly-Supervised Semantic Segmentation
An implementation of Covariance Pooling, with the framwork of AlexNet and the dataset of UC Merced
Regularizing Class-wise Predictions via Self-knowledge Distillation (CVPR 2020)
Dense Attention Fluid Network for Salient Object Detection in Optical Remote Sensing Images
Easy to use pytorch-implementation of DDRNet on Cityscapes dataset
Database and code of our MICCAI20 paper: "DeepGF: Glaucoma Forecast Using the Sequential Fundus Images"
[Preprint] "Improved Techniques for Learning to Dehaze and Beyond: A Collective Study"
High Quality Monocular Depth Estimation via Transfer Learning
Using DenseNet121 for very high resolution scene classification
Use DenseNet40 for remote sensing image scene classification
official implementation of the proposed decoupled feature query (DFQ)