Meta-Learning and Self-Supervised Pretraining for Few-shot Image Translation
Recent advances in machine learning (ML) and deep learning in particular, enabled by hardware advances and big data, have provided impressive results across a wide range of computational problems such as computer vision, natural language, or reinforcement learning. Many of these improvements are how...
Main Author: | Rugina, Ileana |
---|---|
Other Authors: | Soljačić, Marin |
Format: | Thesis |
Published: |
Massachusetts Institute of Technology
2022
|
Online Access: | https://hdl.handle.net/1721.1/139025 |
Similar Items
-
Meta-learning for semi-supervised few-shot classification
by: Tenenbaum, Joshua B
Published: (2020) -
Few-shot contrastive transfer learning with pretrained model for masked face verification
by: Weng, Zhenyu, et al.
Published: (2024) -
Few-Shot Semi-Supervised Robust Text Classification with MAML
by: Kang, Isabella
Published: (2022) -
Visual Language Pretrained Multiple Instance Zero-Shot
Transfer for Histopathology Images
by: Lu, Ming Yang (Max)
Published: (2023) -
Structural Supervision Improves Few-Shot Learning and Syntactic Generalization in Neural Language Models
by: Wilcox, Ethan, et al.
Published: (2021)