Litcius/Paper detail

Few-shot Image Classification: Just Use a Library of Pre-trained Feature Extractors and a Simple Classifier

Arkabandhu Chowdhury, Mingchao Jiang, Swarat Chaudhuri, Chris Jermaine

20212021 IEEE/CVF International Conference on Computer Vision (ICCV)33 citationsDOI

Abstract

Recent papers have suggested that transfer learning can outperform sophisticated meta-learning methods for few-shot image classification. We take this hypothesis to its logical conclusion, and suggest the use of an ensemble of high-quality, pre-trained feature extractors for few-shot image classification. We show experimentally that a library of pre-trained feature extractors combined with a simple feed-forward network learned with an L2-regularizer can be an excellent option for solving cross-domain few-shot image classification. Our experimental results suggest that this simple approach far outperforms several well-established meta-learning algorithms.

Topics & Concepts

Computer scienceArtificial intelligencePattern recognition (psychology)Classifier (UML)Contextual image classificationFeature (linguistics)Feature extractionSimple (philosophy)Machine learningShot (pellet)Image (mathematics)Transfer of learningOne shotFeature vectorEngineeringMechanical engineeringChemistryPhilosophyLinguisticsEpistemologyOrganic chemistryDomain Adaptation and Few-Shot LearningCancer-related molecular mechanisms researchMultimodal Machine Learning Applications
Few-shot Image Classification: Just Use a Library of Pre-trained Feature Extractors and a Simple Classifier | Litcius