Comparative Analysis of Self-Supervised Pretraining and Normalization for Few-Shot Classification on High-Dimensional Synthetic

Deep convolutional neural networks have performed remarkably well on many Computer Vision tasks. However, these networks are heavily reliant on big data to avoid overfitting. Overfitting refers to the phenomenon when a network learns a function with very high variance such as to perfectly model the training data. Unfortunately, many application domains do not have access to big data, such as medical image analysis. This survey focuses on Data Augmentation, a data-space solution to the problem of limited data. Data Augmentation encompasses a suite of techniques that enhance the size and quality

Research goal: How do self-supervised tabular pretraining methods compare to standard normalization techniques in improving few-shot classification accuracy on high-dimensional UCI synthetic benchmarks?

Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 8.7/10.