Xingyu Chen's repositories
DDRNet
The official implementation of "Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes"
Language:PythonMIT000
LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning: LLaVA (Large Language-and-Vision Assistant) built towards GPT-4V level capabilities.
Language:PythonApache-2.0000
LoFTR
Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021
Language:Jupyter NotebookApache-2.0000
Parallel_net
Parallel_google_net/Dense_net/Res_net
Language:Python000
Probabilistic-Face-Embeddings
(ICCV 2019) Uncertainty-aware Face Representation and Recognition
Language:PythonMIT000
Semi-supervised-learning
Traditional & Deep semi-supervised learning algorithms
Language:Python000
VisualRecognition-NomMer
Code for CVPR 2022 paper "NomMer: Nominate Synergistic Context in Vision Transformer for Visual Recognition"
Language:PythonNOASSERTION000