Data to 7 Oct 2026

Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning

arXiv 2003.04390 ↗First posted 9 Mar 2020cs.CV cs.LGcited by 179

Not on the map. Why?

Abstract (arXiv)

Meta-learning has been the most common framework for few-shot learning in recent years. It learns the model from collections of few-shot classification tasks, which is believed to have a key advantage of making the training objective consistent with the testing objective. However, some recent works report that by training for whole-classification, i.e. classification on the whole label-set, it can get comparable or even better embedding than many meta-learning algorithms. The edge between these two lines of works has yet been underexplored, and the effectiveness of meta-learning in few-shot learning remains unclear. In this paper, we explore a simple process: meta-learning over a whole-classification pre-trained model on its evaluation metric. We observe this simple method achieves competitive performance to state-of-the-art methods on standard benchmarks. Our further analysis shed some light on understanding the trade-offs between the meta-learning objective and the whole-classification objective in few-shot learning.

Key facts. Cited by 179 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 47; 2023: 49; 2024: 43; 2025: 20; 2026: 8.

179 papers.

Sort:

By area:

2022Matryoshka Representation Learningcited by 268
2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
2023Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learnerscited by 152
2022Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Differencecited by 123
2021PartImageNet: A Large, High-Quality Dataset of Partscited by 107
2022"This is my unicorn, Fluffy": Personalizing frozen vision-language representationscited by 95
2023Advances and Challenges in Meta-Learning: A Technical Reviewcited by 65
2021Rectifying the Shortcut Learning of Background for Few-Shot Learningcited by 51
2022Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classificationcited by 50
2022Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-Expertscited by 50
2023Text-guided Foundation Model Adaptation for Pathological Image Classificationcited by 47
2023A Closer Look at Few-shot Classification Againcited by 46

38 more

2022A Modern Self-Referential Weight Matrix That Learns to Modify Itselfcited by 40
2023MetaDiff: Meta-Learning with Conditional Diffusion for Few-Shot Learningcited by 40
2022Generating Representative Samples for Few-Shot Classificationcited by 39
2023MedFMC: A Real-world Dataset and Benchmark For Foundation Model Adaptation in Medical Image Classificationcited by 38
2024Diffusion-Based Neural Network Weights Generationcited by 38
2022A Review of Emerging Research Directions in Abstract Visual Reasoningcited by 33
2022Few-Shot Classification with Contrastive Learningcited by 31
2023Semantic Prompt for Few-Shot Image Recognitioncited by 29
2023Learn to Accumulate Evidence from All Training Samples: Theory and Practicecited by 28
2024Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Modelscited by 28
2022Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learningcited by 27
2022Matching Feature Sets for Few-Shot Image Classificationcited by 25
2022AcroFOD: An Adaptive Method for Cross-domain Few-shot Object Detectioncited by 25
2022MetaAudio: A Few-Shot Audio Classification Benchmarkcited by 24
2023Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification & Segmentationcited by 24
2022Self-Promoted Supervision for Few-Shot Transformercited by 22
2022Channel Importance Matters in Few-Shot Image Classificationcited by 20
2022Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroidcited by 20
2023Context-Aware Meta-Learningcited by 20
2024IC3M: In-Car Multimodal Multi-object Monitoring for Abnormal Status of Both Driver and Passengerscited by 20
2023BIRB: A Generalization Benchmark for Information Retrieval in Bioacousticscited by 19
2022On the Effectiveness of Fine-tuning Versus Meta-reinforcement Learningcited by 18
2023From Google Gemini to OpenAI Q* (Q-Star): A Survey of Reshaping the Generative Artificial Intelligence (AI) Research Landscapecited by 18
2021A Closer Look at Few-Shot Video Classification: A New Baseline and Benchmarkcited by 16
2022Few-Shot Learning Meets Transformer: Unified Query-Support Transformers for Few-Shot Classificationcited by 16
2021Rich Semantics Improve Few-shot Learningcited by 15
2022Accumulated Trivial Attention Matters in Vision Transformers on Small Datasetscited by 15
2023ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusioncited by 15
2023Simple Semantic-Aided Few-Shot Learningcited by 15
2021Disentangled Feature Representation for Few-shot Image Classificationcited by 12
2023One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matchingcited by 12
2024Meta-Exploiting Frequency Prior for Cross-Domain Few-Shot Learningcited by 11
2022Weak-shot Semantic Segmentation via Dual Similarity Transfercited by 10
2022Evidential Conditional Neural Processescited by 10
2024Boosting Few-Shot Learning via Attentive Feature Regularizationcited by 10
2023Image Synthesis under Limited Data: A Survey and Taxonomycited by 9
2023From Channel Bias to Feature Redundancy: Uncovering the "Less is More" Principle in Few-Shot Learningcited by 9
2021Task Affinity with Maximum Bipartite Matching in Few-Shot Learningcited by 8

50 most cited of 179 All 179 (JSON)