Hello there! I'm Xiang An.
I'm a Computer Engineering.
-
Large-scale Vision Model Trained on LAION400M and COYO700M with Weak Supervision in ECCV2024:
Multi-label Cluster Discrimination for Visual Representation Learning -
High-Fidelity Facial Albedo, trained on WebFace260M:
High-Fidelity Facial Albedo Estimation via Texture Quantization -
Vision RWKV Pretrain:
RWKV-CLIP: A Robust Vision-Language Representation Learner in EMNLP2024 -
Personalized Face Generation:
IDAdapter: Learning Mixed Features for Tuning-Free Personalization of Text-to-Image Models in CVPRW2024 -
Language-Image Pre-training with Synthetic Caption:
ALIP: Adaptive Language-Image Pre-training with Synthetic Caption in ICCV2023 -
Large-scale Vision Model Trained on LAION400M with Weak Supervision:
UNICOM: Universal and Compact Representation Learning for Image Retrieval in ICLR2023 -
Distributed and Hybrid Parallel Large-Scale Classification Algorithm, trained on WebFace260M:
Partial FC:Efficient and Robust Training of Face Recognition CNNs by Partial FC in CVPR2022