# Few-Shot Image Classification Benchmarks are Too Far From Reality: Build Back Better with Semantic Task Sampling

arXiv: https://arxiv.org/abs/2205.05155 · HTML: https://mlsanity.com/paper/2205.05155/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 35 references that are in the map.
- First posted on arXiv 10 May 2022.

## Builds on (most cited first, 20 of 20)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [A Closer Look at Few-shot Classification](https://mlsanity.com/paper/1904.04232/) (2019)
- [Meta-Learning for Semi-Supervised Few-Shot Classification](https://mlsanity.com/paper/1803.00676/) (2018)
- [Meta-learning with differentiable closed-form solvers](https://mlsanity.com/paper/1805.08136/) (2018)
- [Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples](https://mlsanity.com/paper/1903.03096/) (2019)
- [A Baseline for Few-Shot Image Classification](https://mlsanity.com/paper/1909.02729/) (2019)
- [Task2Vec: Task Embedding for Meta-Learning](https://mlsanity.com/paper/1902.03545/) (2019)
- [Prototype Rectification for Few-Shot Learning](https://mlsanity.com/paper/1911.10713/) (2019)
- [Leveraging the Feature Distribution in Transfer-based Few-Shot Learning](https://mlsanity.com/paper/2006.03806/) (2020)
- [Transductive Information Maximization For Few-Shot Learning](https://mlsanity.com/paper/2008.11297/) (2020)
- [Revisiting Pose-Normalization for Fine-Grained Few-Shot Recognition](https://mlsanity.com/paper/2004.00705/) (2020)
- [Adaptive Task Sampling for Meta-Learning](https://mlsanity.com/paper/2007.08735/) (2020)
- [Danish Fungi 2020 -- Not Just Another Image Recognition Dataset](https://mlsanity.com/paper/2103.10107/) (2021)
- [Variational Feature Disentangling for Fine-Grained Few-Shot Classification](https://mlsanity.com/paper/2010.03255/) (2020)
- [Adaptive Posterior Learning: few-shot learning with a surprise-based memory module](https://mlsanity.com/paper/1902.02527/) (2019)
- [Comparing Transfer and Meta Learning Approaches on a Unified Few-Shot Classification Benchmark](https://mlsanity.com/paper/2104.02638/) (2021)
- [Similarity of Classification Tasks](https://mlsanity.com/paper/2101.11201/) (2021)

## Built on by (most cited first, 1 of 1)

- [In-Context Adaptation of VLMs for Few-Shot Cell Detection in Optical Microscopy](https://mlsanity.com/paper/2511.05565/) (2025)

## Abstract (arXiv)

Every day, a new method is published to tackle Few-Shot Image Classification, showing better and better performances on academic benchmarks. Nevertheless, we observe that these current benchmarks do not accurately represent the real industrial use cases that we encountered. In this work, through both qualitative and quantitative studies, we expose that the widely used benchmark tieredImageNet is strongly biased towards tasks composed of very semantically dissimilar classes e.g. bathtub, cabbage, pizza, schipperke, and cardoon. This makes tieredImageNet (and similar benchmarks) irrelevant to evaluate the ability of a model to solve real-life use cases usually involving more fine-grained classification. We mitigate this bias using semantic information about the classes of tieredImageNet and generate an improved, balanced benchmark. Going further, we also introduce a new benchmark for Few-Shot Image Classification using the Danish Fungi 2020 dataset. This benchmark proposes a wide variety of evaluation tasks with various fine-graininess. Moreover, this benchmark includes many-way tasks (e.g. composed of 100 classes), which is a challenging setting yet very common in industrial applications. Our experiments bring out the correlation between the difficulty of a task and the semantic similarity between its classes, as well as a heavy performance drop of state-of-the-art methods on many-way few-shot classification, raising questions about the scaling abilities of these methods. We hope that our work will encourage the community to further question the quality of standard evaluation processes and their relevance to real-life applications.