-
DINE: Domain Adaptation from Single and Multiple Black-box Predictors
SOTA domain adaptation for object detection
-
MobileOne: An Improved One millisecond Mobile Backbone
SOTA model of mobile backbone
-
Proper Reuse of Image Classification Features Improves Object Detection
Neck is important
-
Meta Pseudo Labels
SOTA cnn technique on imagenet
-
MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
transformer for mobile device