Search Results for author:
Found 3 papers, 3 papers with code
Automatic Data Curation for Self-Supervised Learning: A Clustering-Based Approach
This manual process has some limitations similar to those encountered in supervised learning, e. g., the crowd-sourced selection of data is costly and time-consuming, preventing scaling the dataset size.
Vision Transformers Need Registers
Transformers have recently emerged as a powerful tool for learning visual representations.
DINOv2: Learning Robust Visual Features without Supervision
The recent breakthroughs in natural language processing for model pretraining on large quantities of data have opened the way for similar foundation models in computer vision.
Ranked #1 on
Image Retrieval
on AmsterTime
(using extra training data)
