Deep High-Resolution Representation Learning for Visual Recognition
Paper
•
1908.07919
•
Published
•
2
Bin Xiao
leoxiaobin
AI & ML interests
Large-scale Foundation Model Training; Computer Vision; Deep Learning
Recent Activity
new activity
about 7 hours ago
microsoft/Florence-2-base:add confidence scores for `od` and `description_with_bboxes` tasks
new activity
about 8 hours ago
microsoft/Florence-2-base:Fix invalid escape sequences
new activity
about 8 hours ago
microsoft/Florence-2-base:Fix the error "only DaViT is supported for now" appears whenloading the fine-tuned model
Organizations
authored
10
papers
over 1 year ago
CvT: Introducing Convolutions to Vision Transformers
Paper
•
2103.15808
•
Published
DaViT: Dual Attention Vision Transformers
Paper
•
2204.03645
•
Published
TinyViT: Fast Pretraining Distillation for Small Vision Transformers
Paper
•
2207.10666
•
Published
•
2
TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance
Paper
•
2309.12314
•
Published
•
2
MiniViT: Compressing Vision Transformers with Weight Multiplexing
Paper
•
2204.07154
•
Published
•
1
Lite-HRNet: A Lightweight High-Resolution Network
Paper
•
2104.06403
•
Published
Deep High-Resolution Representation Learning for Human Pose Estimation
Paper
•
1902.09212
•
Published
Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks
Paper
•
2311.06242
•
Published
•
94
Florence: A New Foundation Model for Computer Vision
Paper
•
2111.11432
•
Published
•
3