Meta-Learning and Self-Supervised Pretraining for Real World Image Translation

2021-12-22 · Ileana Rugina, Rumen Dangovski, Mark Veillette, Pooya Khorrami, Brian Cheung, Olga Simek, Marin Soljačić

Recent advances in 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 however constrained to problems with large-scale curated data-sets which require a lot of human labor to gather. Additionally, these models tend to generalize poorly under both slight distributional shifts and low-data regimes. In recent years, emerging fields such as meta-learning or self-supervised learning have been closing the gap between proof-of-concept results and real-life applications of machine learning by extending deep-learning to the semi-supervised and few-shot domains. We follow this line of work and explore spatio-temporal structure in a recently introduced image-to-image translation problem in order to: i) formulate a novel multi-task few-shot image generation benchmark and ii) explore data augmentations in contrastive pre-training for image translation downstream tasks. We present several baselines for the few-shot problem and discuss trade-offs between different approaches. Our code is available at https://github.com/irugina/meta-image-translation.

📄 PDF Abstract BibTeX arXiv:2112.11929

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation Image-to-Image Translation Meta-Learning Self-Supervised Learning Translation

GUST: Quantifying Free-Form Geometric Uncertainty of Metamaterials Using Small Data

2025-05-28 · Jiahui Zheng, Cole Jahnke, Wei "Wayne" Chen

This paper introduces GUST (Generative Uncertainty learning via Self-supervised pretraining and Transfer learning), a framework for quantifying free-form geometric uncertainties inherent in the manufacturing of metamater…

Form Transfer Learning Uncertainty Quantification

Learning to diagnose cirrhosis from radiological and histological labels with joint self and weakly-supervised pretraining strategies

2023-02-16 · Emma Sarfati, Alexandre Bone, Marc-Michel Rohe, Pietro Gori 외

Identifying cirrhosis is key to correctly assess the health of the liver. However, the gold standard diagnosis of the cirrhosis needs a medical intervention to obtain the histological confirmation, e.g. the METAVIR score…

Transfer Learning

Transductive Linear Probing: A Novel Framework for Few-Shot Node Classification

2022-12-11 · Zhen Tan, Song Wang, Kaize Ding, Jundong Li 외

Few-shot node classification is tasked to provide accurate predictions for nodes from novel classes with only few representative labeled nodes. This problem has drawn tremendous attention for its projection to prevailing…

Classification Contrastive Learning Meta-Learning Node Classification+2

On the Effectiveness of Fine-tuning Versus Meta-reinforcement Learning

2022-06-07 · Zhao Mandi, Pieter Abbeel, Stephen James

Intelligent agents should have the ability to leverage knowledge from previously learned tasks in order to learn new ones quickly and efficiently. Meta-learning approaches have emerged as a popular solution to achieve th…

Meta-Learning Meta Reinforcement Learning reinforcement-learning Reinforcement Learning+3

MatSSL: Robust Self-Supervised Representation Learning for Metallographic Image Segmentation

2025-07-24 · Hoang Hai Nam Nguyen, Phan Nguyen Duc Hieu, Ho Won Lee arxiv

MatSSL is a streamlined self-supervised learning (SSL) architecture that employs Gated Feature Fusion at each stage of the backbone to integrate multi-level representations effectively. Current micrograph analysis of met…

Self-Supervised Learning Representation Learning Image Segmentation