Hello there! I'm Xiang An.
I'm a Computer Engineering.

• Large-scale Vision Model Trained onLAION400M andCOYO700M with Weak Supervision inECCV2024:
  Multi-label Cluster Discrimination for Visual Representation Learning

• Large-scale Vision Model Trained onLAION400M with Weak Supervision:
  UNICOM: Universal and Compact Representation Learning for Image Retrieval inICLR2023

• Distributed and Hybrid Parallel Large-Scale Classification Algorithm, trained onWebFace260M:
  Partial FC: Efficient and Robust Training of Face Recognition CNNs by Partial FC inCVPR2022

If you are interested in joining our team, please send your resume toxiangan@deepglint.com. We look forward to advancing the frontiers ofVision andVideo Pretraining together with you!

PinnedLoading

1. deepinsight/insightfacedeepinsight/insightfacePublic

   State-of-the-art 2D and 3D Face Analysis Project

   Python 24.7k 5.5k

2. deepglint/unicomdeepglint/unicomPublic

   Large-Scale Visual Representation Model

   Python 650 27

3. LLaVA-VL/LLaVA-NeXTLLaVA-VL/LLaVA-NeXTPublic

   Python 3.6k 334

4. urban_segurban_segPublic

   Remotes Sensing Semantic Segmentation

   Python 435 140

5. daixiangzi/VAR-CLIPdaixiangzi/VAR-CLIPPublic

   Implements VAR+CLIP for text-to-image (T2I) generation

   Python 131 3

6. OpenVFM/V-SWIFTOpenVFM/V-SWIFTPublic

   V-SWIFT: Training a Small VideoMAE Model on a Single Machine in a Day

   Python 28 1