Uniform Priors for Data-Efficient Transfer
원문 초록
Deep Neural Networks have shown great promise on a variety of downstream applications; but their ability to adapt and generalize to new data and tasks remains a challenge. However, the ability to perform few or zero-shot adaptation to novel tasks is important for the scalability and deployment of machine learning models. It is therefore crucial to understand what makes for good, transfer-able features in deep networks that best allow for such adaptation. In this paper, we shed light on this by showing that features that are most transferable have high uniformity in the embedding space and propose a uniformity regularization scheme that encourages better transfer and feature reuse. We evaluate the regularization on its ability to facilitate adaptation to unseen tasks and data, for which we conduct a thorough experimental study covering four relevant, and distinct domains: few-shot Meta-Learning, Deep Metric Learning, Zero-Shot Domain Adaptation, as well as Out-of-Distribution classification. Across all experiments, we show that uniformity regularization consistently offers benefits over baseline methods and is able to achieve state-of-the-art performance in Deep Metric Learning and Meta-Learning.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Are encoders able to learn landmarkers for warm-starting of Hyperparameter Optimization?
The Bayesian Approach to Continual Learning: An Overview
Few-Shot Learning for Industrial Time Series: A Comparative Analysis Using the Example of Screw-Fastening Process Monitoring
Domain Borders Are There to Be Crossed With Federated Few-Shot Adaptation
Geo-ORBIT: A Federated Digital Twin Framework for Scene-Adaptive Lane Geometry Detection
UMDATrack: Unified Multi-Domain Adaptive Tracking Under Adverse Weather Conditions
토론
이 논문과 연결된 포럼 글이 아직 없습니다.