Picture for Yaoming Wang

Yaoming Wang

Learning Unsupervised Gaze Representation via Eye Mask Driven Information Bottleneck

Add code
Jun 29, 2024
Viaarxiv icon

Parameter-efficient Fine-tuning in Hyperspherical Space for Open-vocabulary Semantic Segmentation

Add code
May 29, 2024
Viaarxiv icon

UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding

Add code
Jan 18, 2024
Viaarxiv icon

AiluRus: A Scalable ViT Framework for Dense Prediction

Add code
Nov 02, 2023
Viaarxiv icon

Hybrid Distillation: Connecting Masked Autoencoders with Contrastive Learners

Add code
Jun 28, 2023
Viaarxiv icon