Abstract:
Deep learning, in general, focuses on training a neural network from large labeled datasets. Yet, in many cases, there is value in training a network just from the input ...Show MoreMetadata
Abstract:
Deep learning, in general, focuses on training a neural network from large labeled datasets. Yet, in many cases, there is value in training a network just from the input at hand. This is particularly relevant in many signal and image processing problems where training data are scarce and diversity is large on the one hand, and on the other, there is a lot of structure in the data that can be exploited. Using this information is the key to deep internal learning strategies, which may involve training a network from scratch using a single input or adapting an already trained network to a provided input example at inference time. This survey article aims at covering deep internal learning techniques that have been proposed in the past few years for these two important directions. While our main focus is on image processing problems, most of the approaches that we survey are derived for general signals (vectors with recurring patterns that can be distinguished from noise) and are therefore applicable to other modalities.
Published in: IEEE Signal Processing Magazine ( Volume: 41, Issue: 4, July 2024)
Funding Agency:
Keywords assist with retrieval of results and provide a means to discovering other relevant content. Learn more.
- IEEE Keywords
- Index Terms
- Deep Learning ,
- Internal Learning ,
- Deep Internal Learning ,
- Neural Network ,
- Training Data ,
- Signal Processing ,
- Inference Time ,
- Image Processing Problems ,
- Convolutional Neural Network ,
- Deep Neural Network ,
- Generative Adversarial Networks ,
- Natural Images ,
- Early Stopping ,
- Clear Image ,
- Massive Amounts Of Data ,
- Deep Neural Network Architecture ,
- Latent Vector ,
- Encoder Network ,
- Random Input ,
- Deep Neural Network Parameters ,
- Unknown Image ,
- Data Fidelity Term ,
- Latent Image ,
- Mean Square Error Criterion ,
- Super-resolution Task ,
- Proximal Operator ,
- Least Squares Loss ,
- Ground Truth Image ,
- Iterative Optimization
Keywords assist with retrieval of results and provide a means to discovering other relevant content. Learn more.
- IEEE Keywords
- Index Terms
- Deep Learning ,
- Internal Learning ,
- Deep Internal Learning ,
- Neural Network ,
- Training Data ,
- Signal Processing ,
- Inference Time ,
- Image Processing Problems ,
- Convolutional Neural Network ,
- Deep Neural Network ,
- Generative Adversarial Networks ,
- Natural Images ,
- Early Stopping ,
- Clear Image ,
- Massive Amounts Of Data ,
- Deep Neural Network Architecture ,
- Latent Vector ,
- Encoder Network ,
- Random Input ,
- Deep Neural Network Parameters ,
- Unknown Image ,
- Data Fidelity Term ,
- Latent Image ,
- Mean Square Error Criterion ,
- Super-resolution Task ,
- Proximal Operator ,
- Least Squares Loss ,
- Ground Truth Image ,
- Iterative Optimization