New DeepMind Approach ‘Bootstraps’ Self-Supervised Learning of Image Representations | Synced
From an augmented view of an image, the researchers trained the online network to predict the target network representation of the same image under a different augmented view.
- computer vision & graphics
- machine learning & data science
- artificial intelligence
- computer vision
- deepmind
Source: Synced | AI Technology & Industry Review
From an augmented view of an image, the researchers trained the online network to predict the target network representation of the same image under a different augmented view.