Laplacian Regularized Few-Shot Learning

Abstract

We propose a transductive Laplacian-regularized inference for few-shot tasks. Given any feature embedding learned from the base classes, we minimize a quadratic binary-assignment function containing two terms: (1) a unary term assigning query samples to the nearest class prototype, and (2) a pairwise Laplacian term encouraging nearby query samples to have consistent label assignments. Our transductive inference does not re-train the base model, and can be viewed as a graph clustering of the query set, subject to supervision constraints from the support set. We derive a computationally efficient bound optimizer of a relaxation of our function, which computes independent (parallel) updates for each query sample, while guaranteeing convergence. Following a simple cross-entropy training on the base classes, and without complex meta-learning strategies, we conducted comprehensive experiments over five few-shot learning benchmarks. Our LaplacianShot consistently outperforms state-of-the-art methods by significant margins across different models, settings, and data sets. Furthermore, our transductive inference is very fast, with computational times that are close to inductive inference, and can be used for large-scale few-shot tasks.

arXiv commentICML 2020 paper

Cited by in corpus (12)

• Transductive Information Maximization For Few-Shot Learning
• MHFC: Multi-Head Feature Collaboration for Few-Shot Learning
• GCT: Graph Co-Training for Semi-Supervised Few-Shot Learning
• Few-Shot Learning with Uncertainty-based Quadruplet Selection for Interference Classification in GNSS Data
• Graph Signal Processing for Geometric Data and Beyond: Theory and Applications
• Temporal Alignment Prediction for Few-Shot Video Classification
• Transductive Few-Shot Learning: Clustering is All You Need?
• Few-shot Learning with Global Relatedness Decoupled-Distillation
• A Transductive Maximum Margin Classifier for Few-Shot Learning
• One-shot Learning with Absolute Generalization
• Transductive Learning for Textual Few-Shot Classification in API-based Embedding Models
• Mutual-Information Based Few-Shot Classification