paper-with-me

Papers

Laplacian Regularized Few-Shot Learning

2020-06-29 · ICML 2020 1 · Imtiaz Masud Ziko; Jose Dolz; Eric Granger; Ismail Ben Ayed

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 assign- ing query samples to the nearest class prototype, and (2) a pairwise Laplacian term encouraging nearby query samples to have consistent label as- signments. Our transductive inference does not re-train the base model, and can be viewed as a graph clustering of the query set, subject to super- vision constraints from the support set. We derive a computationally efficient bound optimizer of a relaxation of our function, which computes inde- pendent (parallel) updates for each query sample, while guaranteeing convergence. Following a sim- ple cross-entropy training on the base classes, and without complex meta-learning strategies, we con- ducted 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 trans- ductive inference is very fast, with computational times that are close to inductive inference, and can be used for large-scale few-shot tasks.

📄 PDF Abstract BibTeX

Code (2)

imtiazziko/LaplacianShot pytorch
sicara/easy-few-shot-learning pytorch

Tasks

ClusteringFew-Shot Image ClassificationFew-Shot LearningGraph ClusteringMeta-Learning

Methods 이 논문이 사용한 방법론

Transductive Inference 설명 없음

Similar Papers 제목 키워드 기반

Laplacian Regularized Few-Shot Learning

2020-06-28 · Imtiaz Masud Ziko, Jose Dolz, Eric Granger, Ismail Ben Ayed

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 unar…

ClusteringFew-Shot Image ClassificationFew-Shot LearningGraph Clustering+1

Semi-supervised Learning with Regularized Laplacian

2015-08-20 · Konstantin Avrachenkov, Pavel Chebotarev, Alexey Mishenin

We study a semi-supervised learning method based on the similarity graph and RegularizedLaplacian. We give convenient optimization formulation of the Regularized Laplacian method and establishits various properties. In p…

General Classification

Regularized Laplacian Estimation and Fast Eigenvector Approximation

2011-12-01 · NeurIPS 2011 12 · Patrick O. Perry, Michael W. Mahoney

Recently, Mahoney and Orecchia demonstrated that popular diffusion-based procedures to compute a quick approximation to the first nontrivial eigenvector of a data graph Laplacian exactly solve certain regularized Semi-De…

regression

Dual regularized Laplacian spectral clustering methods on community detection

2020-11-09 · Huan Qing, Jingli Wang

Spectral clustering methods are widely used for detecting clusters in networks for community detection, while a small change on the graph Laplacian matrix could bring a dramatic improvement. In this paper, we propose a d…

ClusteringCommunity DetectionStochastic Block Model

Difference-of-Convex Regularization for Graph Learning by Differentiable Programming

2026-08-13 · Liping Tao, Chee Wei Tan arxiv

Laplacian-regularized minimization is fundamental in signal processing and machine learning, but is limited by the dense and ill-conditioned nature of the graph Laplacian pseudoinverse. While the Laplacian itself is spar…

Graph Learning