Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes
This talk will describe our recent work on designing image classification systems that, after an initial multi-task training phase, can automatically adapt to new tasks encountered at test time. I will introduce an approach that relates to existing approaches to meta-learning and so-called conditional neural processes, generalising them to the multi-task classification setting. The resulting approach, called Conditional Neural Adaptive Processes (CNAPS), comprises a classifier whose parameters are modulated by an adaptation network that takes the current task's dataset as input. I will show that CNAPS achieves state-of-the-art results on the challenging Meta-Dataset few-shot learning benchmark indicating high-quality transfer-learning which is robust, avoiding both over-fitting in low-shot regimes and under-fitting in high-shot regimes. Timing experiments reveal that CNAPS is computationally efficient at test-time as it does not involve gradient based adaptation. Finally, I will show that trained models are immediately deployable to continual learning and active learning where they can outperform existing approaches that do not leverage transfer learning.
See more at https://www.microsoft.com/en-us/research/video/fast-and-flexible-multi-task-classification-using-conditional-neural-adaptive-processes/
Видео Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes канала Microsoft Research
See more at https://www.microsoft.com/en-us/research/video/fast-and-flexible-multi-task-classification-using-conditional-neural-adaptive-processes/
Видео Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes канала Microsoft Research
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
The Intern Experience at Microsoft Research CambridgeBattling Tuberculosis Using Microsoft TechnologyData Visualization Reaches New Heights with LayerscapeFaculty Summit 2018 IntroductionMicrosoft Pix - Take Better Photos of People, AutomaticallyImprovements on Higher Order Ambisonics ReproductionCambridge lab overview with Chris BishopGet free cloud computing time and storage on Microsoft AzureHow interns at our New England Lab impact research at MicrosoftAI Institute "Geometry of Deep Learning" 2019 [Workshop] Day 1 | Session 2De-Identifying Healthcare Data for ResearchIntelligent cloud computing lifts villages out of water povertyHow Microsoft and Novartis created Assess MS (short version)How OSIsoft and Deschutes Brewery used Microsoft Security Risk DetectionChronoZoom curriculum and technologyRecent Advances in Image Captioning, Image-Text Retrieval and…Using machine learning and AI to reduce hospital readmissionsIROS 2020 - Mixed Reality and Robotics Tutorial - Demo 1: InteractionCamera-based non-contact health sensingKinect and sign language translation (2:43)