← Search

John Bronskill

4 accepted papers

2021

ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognition

ICCV 2021poster

Object recognition has made great advances in the last decade, but predominately still relies on many high-quality training examples per object category. In contrast, learning new objects from only a few examples could enable many impactful applications from robotics to user personalization. Most fe…

Cited by 57PDFcodeScholar
2020

TaskNorm: Rethinking Batch Normalization for Meta-Learning

ICML 2020poster

Modern meta-learning approaches for image classification rely on increasingly deep networks to achieve state-of-the-art performance, making batch normalization an essential component of meta-learning pipelines. However, the hierarchical nature of the meta-learning setting presents several challenges…

2019

Fast and Flexible Multi-Task Classification using Conditional Neural Adaptive Processes

NeurIPS 2019spotlight

The goal of this paper is to design image classification systems that, after an initial multi-task training phase, can automatically adapt to new tasks encountered at test time. We introduce a conditional neural process based approach to the multi-task classification setting for this purpose, and es…

2019

Meta-Learning Probabilistic Inference for Prediction

ICLR 2019poster

This paper introduces a new framework for data efficient and versatile learning. Specifically: 1) We develop ML-PIP, a general framework for Meta-Learning approximate Probabilistic Inference for Prediction. ML-PIP extends existing probabilistic interpretations of meta-learning to cover a broad class…