# A Baseline for Few-Shot Image Classification

arXiv: https://arxiv.org/abs/1909.02729 · HTML: https://mlsanity.com/paper/1909.02729/

## Key facts

- Cited by 298 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Sep 2019.

## Built on by (most cited first, 30 of 298)

- [Scaling Vision with Sparse Mixture of Experts](https://mlsanity.com/paper/2106.05974/) (2021)
- [ImageNet-21K Pretraining for the Masses](https://mlsanity.com/paper/2104.10972/) (2021)
- [Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling](https://mlsanity.com/paper/2111.03930/) (2021)
- [Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification](https://mlsanity.com/paper/2207.09519/) (2022)
- [FedBABU: Towards Enhanced Representation for Federated Image Classification](https://mlsanity.com/paper/2106.06042/) (2021)
- [StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners](https://mlsanity.com/paper/2306.00984/) (2023)
- [The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning](https://mlsanity.com/paper/2505.15134/) (2025)
- [A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2205.06743/) (2022)
- [Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference](https://mlsanity.com/paper/2204.07305/) (2022)
- [On the Role of Neural Collapse in Transfer Learning](https://mlsanity.com/paper/2112.15121/) (2021)
- [Self-Support Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2207.11549/) (2022)
- [Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning with Multimodal Models](https://mlsanity.com/paper/2301.06267/) (2023)
- [Generalized Few-Shot Object Detection without Forgetting](https://mlsanity.com/paper/2105.09491/) (2021)
- [Learning from Few Examples: A Summary of Approaches to Few-Shot Learning](https://mlsanity.com/paper/2203.04291/) (2022)
- [Cross-domain Few-shot Learning with Task-specific Adapters](https://mlsanity.com/paper/2107.00358/) (2021)
- [Relational Embedding for Few-Shot Classification](https://mlsanity.com/paper/2108.09666/) (2021)
- [FLEX: Unifying Evaluation for Few-Shot NLP](https://mlsanity.com/paper/2107.07170/) (2021)
- [Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weights](https://mlsanity.com/paper/2209.14733/) (2022)
- [Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning](https://mlsanity.com/paper/2103.01315/) (2021)
- [Universal Representation Learning from Multiple Domains for Few-shot Classification](https://mlsanity.com/paper/2103.13841/) (2021)
- [Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classification](https://mlsanity.com/paper/2204.04567/) (2022)
- [A Closer Look at Few-shot Classification Again](https://mlsanity.com/paper/2301.12246/) (2023)
- [Meta-Learning with Fewer Tasks through Task Interpolation](https://mlsanity.com/paper/2106.02695/) (2021)
- [Improved Regularization and Robustness for Fine-tuning in Neural Networks](https://mlsanity.com/paper/2111.04578/) (2021)
- [Universal-Prototype Enhancing for Few-Shot Object Detection](https://mlsanity.com/paper/2103.01077/) (2021)
- [Few-Shot Object Detection via Association and DIscrimination](https://mlsanity.com/paper/2111.11656/) (2021)
- [MedFMC: A Real-world Dataset and Benchmark For Foundation Model Adaptation in Medical Image Classification](https://mlsanity.com/paper/2306.09579/) (2023)
- [Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficulty](https://mlsanity.com/paper/2202.01339/) (2022)
- [Partner-Assisted Learning for Few-Shot Image Classification](https://mlsanity.com/paper/2109.07607/) (2021)
- [Boosting Vision-Language Models with Transduction](https://mlsanity.com/paper/2406.01837/) (2024)

## Abstract (arXiv)

Fine-tuning a deep network trained with the standard cross-entropy loss is a strong baseline for few-shot learning. When fine-tuned transductively, this outperforms the current state-of-the-art on standard datasets such as Mini-ImageNet, Tiered-ImageNet, CIFAR-FS and FC-100 with the same hyper-parameters. The simplicity of this approach enables us to demonstrate the first few-shot learning results on the ImageNet-21k dataset. We find that using a large number of meta-training classes results in high few-shot accuracies even for a large number of few-shot classes. We do not advocate our approach as the solution for few-shot learning, but simply use the results to highlight limitations of current benchmarks and few-shot protocols. We perform extensive studies on benchmark datasets to propose a metric that quantifies the "hardness" of a few-shot episode. This metric can be used to report the performance of few-shot algorithms in a more systematic way.