A Closer Look at Few-shot Classification

2019/04/08 by Wei-Yu Chen, Yen‐Cheng Liu, Chen, Wei-Yu +7 · 29 citations
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning and Data Classification #Multimodal Machine Learning Applications

paper · pdf · doi:10.48550/arxiv.1904.04232

openalex publication_date 2019/04/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Few-shot classification aims to learn a classifier to recognize unseen classes during training with limited labeled examples. While significant progress has been made, the growing complexity of network designs, meta-learning algorithms, and differences in implementation details make a fair comparison difficult. In this paper, we present 1) a consistent comparative analysis of several representative few-shot classification algorithms, with results showing that deeper backbones significantly reduce the performance differences among methods on datasets with limited domain differences, 2) a modified baseline method that surprisingly achieves competitive performance when compared with the state-of-the-art on both the \miniI and the CUB datasets, and 3) a new experimental setting for evaluating the cross-domain generalization ability for few-shot classification algorithms. Our results reveal that reducing intra-class variation is an important factor when the feature backbone is shallow, but not as critical when using deeper backbones. In a realistic cross-domain evaluation setting, we show that a baseline method with a standard fine-tuning practice compares favorably against other state-of-the-art few-shot learning algorithms.

Citations

• Few-Shot Learning with Graph Neural Networks

Cited by

• Few-Shot Learning of a Graph-Based Neural Network Model Without Backpropagation
• Data-Chain Backdoor: Do You Trust Diffusion Models as Generative Data Supplier?
• A Domain-Adapted Lightweight Ensemble for Resource-Efficient Few-Shot Plant Disease Classification
• Basis-Oriented Low-rank Transfer for Few-Shot and Test-Time Adaptation
• Free Lunch to Meet the Gap: Intermediate Domain Reconstruction for Cross-Domain Few-Shot Learning
• Toward Better Generalization in Few-Shot Learning through the Meta-Component Combination
• Neural Variational Dropout Processes
• Enhancing Few-Shot Classification of Benchmark and Disaster Imagery with ATTBHFA-Net
• Connecting Giants: Synergistic Knowledge Transfer of Large Multimodal Models for Few-Shot Learning
• Deep Edge Filter: Return of the Human-Crafted Layer in Deep Learning
• SAFA-SNN: Sparsity-Aware On-Device Few-Shot Class-Incremental Learning with Fast-Adaptive Structure of Spiking Neural Network
• MetaChest: Generalized few-shot learning of pathologies from chest X-rays
• FSMODNet: A Closer Look at Few-Shot Detection in Multispectral Data
• Is Meta-Learning Out? Rethinking Unsupervised Few-Shot Classification with Limited Entropy
• Federated Meta-Learning with Fast Convergence and Efficient Communication
• Adaptive Deep Kernel Learning
• A Discrepancy-Based Perspective on Dataset Condensation
• Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML
• Model-Agnostic Learning to Meta-Learn
• Empirical Bayes Transductive Meta-Learning with Synthetic Gradients
• ST-MAML: A Stochastic-Task based Method for Task-Heterogeneous Meta-Learning
• Learnable Loss Geometries with Mirror Descent for Scalable and Convergent Meta-Learning
• TransMatch: A Transfer-Learning Framework for Defect Detection in Laser Powder Bed Fusion Additive Manufacturing
• Attribute Fusion-based Classifier on Framework of Belief Structure
• Language-Aware Information Maximization for Transductive Few-Shot CLIP
• Data-Efficient Point Cloud Semantic Segmentation Pipeline for Unimproved Roads
• Non-Gaussian Gaussian Processes for Few-Shot Regression
• Object-Centric Cropping for Visual Few-Shot Classification
• FDNAS: Improving Data Privacy and Model Diversity in AutoML
• Shallow Deep Learning Can Still Excel in Fine-Grained Few-Shot Learning

Related

• Few-Shot Classification in Unseen Domains by Episodic Meta-Learning Across Visual Domains
• Few and Fewer: Learning Better from Few Examples Using Fewer Base Classes
• Selecting Relevant Features from a Multi-domain Representation for Few-shot Classification
• A Closer Look at Few-shot Classification Again
• SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning