ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond.
Qiming ZhangYufei XuJing ZhangDacheng TaoPublished in: CoRR (2022)
Keyphrases
- image recognition
- inductive bias
- pattern recognition
- inductive learning
- machine learning
- image classification
- face recognition
- domain theory
- prior knowledge
- image processing
- hypothesis space
- pac learning
- computer vision
- training examples
- domain knowledge
- supervised learning
- neural network
- image analysis
- pairwise
- multitask learning
- sample selection
- graph cuts
- active learning
- training set