Discriminative k-shot learning using probabilistic models

Abstract

This paper introduces a probabilistic framework for k-shot image classification. The goal is to generalise from an initial large-scale classification task to a separate task comprising new classes and small numbers of examples. The new approach not only leverages the feature-based representation learned by a neural network from the initial task (representational transfer), but also information about the classes (concept transfer). The concept information is encapsulated in a probabilistic model for the final layer weights of the neural network which acts as a prior for probabilistic k-shot learning. We show that even a simple probabilistic model achieves state-of-the-art on a standard k-shot learning dataset by a large margin. Moreover, it is able to accurately model uncertainty, leading to well calibrated classifiers, and is easily extensible and flexible, unlike many recent approaches to k-shot learning.

Cited by in corpus (17)

• SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning
• Meta-Learning with Latent Embedding Optimization
• TADAM: Task dependent adaptive metric for improved few-shot learning
• Bayesian Model-Agnostic Meta-Learning
• Learning from Few Samples: A Survey
• Self-Supervised Learning For Few-Shot Image Classification
• Relational Generalized Few-Shot Learning
• Reconciling meta-learning and continual learning with online mixtures of tasks
• Meta-Learning surrogate models for sequential decision making
• Uncertainty in Multitask Transfer Learning
• MetaFun: Meta-Learning with Iterative Functional Updates
• Adaptive Cross-Modal Few-Shot Learning
• Decoder Choice Network for Meta-Learning
• Adaptive Wasserstein Hourglass for Weakly Supervised Hand Pose Estimation from Monocular RGB
• Uncertainty-Aware Few-Shot Image Classification
• Learning by Examples Based on Multi-level Optimization
• A Transductive Maximum Margin Classifier for Few-Shot Learning