# Frozen Feature Augmentation for Few-Shot Image Classification

arXiv: https://arxiv.org/abs/2403.10519 · HTML: https://mlsanity.com/paper/2403.10519/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 60 of its 78 references that are in the map.
- First posted on arXiv 15 Mar 2024.

## Builds on (most cited first, 30 of 60)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [Scaling Vision Transformers](https://mlsanity.com/paper/2106.04560/) (2021)
- [Revisiting Unreasonable Effectiveness of Data in Deep Learning Era](https://mlsanity.com/paper/1707.02968/) (2017)
- [Adafactor: Adaptive Learning Rates with Sublinear Memory Cost](https://mlsanity.com/paper/1804.04235/) (2018)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Remote Sensing Image Scene Classification: Benchmark and State of the Art](https://mlsanity.com/paper/1703.00121/) (2017)

## Built on by (most cited first, 13 of 13)

- [Multimodal Whole Slide Foundation Model for Pathology](https://mlsanity.com/paper/2411.19666/) (2024)
- [CARE: A Molecular-Guided Foundation Model with Adaptive Region Modeling for Whole Slide Image Analysis](https://mlsanity.com/paper/2602.21637/) (2026)
- [No Train, all Gain: Self-Supervised Gradients Improve Deep Frozen Representations](https://mlsanity.com/paper/2407.10964/) (2024)
- [Exact Federated Continual Unlearning for Ridge Heads on Frozen Foundation Models](https://mlsanity.com/paper/2603.12977/) (2026)
- [Slot Attention-based Feature Filtering for Few-Shot Learning](https://mlsanity.com/paper/2508.09699/) (2025)
- [Prompt-Driven Simulation with Feature Perturbation for Cross-Domain Few-Shot Object Detection](https://mlsanity.com/paper/2608.01348/) (2026)
- [Group Relative Augmentation for Data Efficient Action Detection](https://mlsanity.com/paper/2507.21353/) (2025)
- [Color as the Impetus: Transforming Few-Shot Learner](https://mlsanity.com/paper/2507.22136/) (2025)
- [Denoised Diffusion for Object-Focused Image Augmentation](https://mlsanity.com/paper/2510.08955/) (2025)
- [ReCCur: A Recursive Corner-Case Curation Framework for Robust Vision-Language Understanding in Open and Edge Scenarios](https://mlsanity.com/paper/2601.03011/) (2026)
- [VidPrism: Heterogeneous Mixture of Experts for Image-to-Video Transfer](https://mlsanity.com/paper/2605.28229/) (2026)
- [FACT: A Simple and Efficient Framework for Active Finetuning](https://mlsanity.com/paper/2606.02079/) (2026)
- [Whitening Improves Robustness to Spurious Correlations in Linear Probes](https://mlsanity.com/paper/2609.39177/) (2026)

## Abstract (arXiv)

Training a linear classifier or lightweight model on top of pretrained vision model outputs, so-called 'frozen features', leads to impressive performance on a number of downstream few-shot tasks. Currently, frozen features are not modified during training. On the other hand, when networks are trained directly on images, data augmentation is a standard recipe that improves performance with no substantial overhead. In this paper, we conduct an extensive pilot study on few-shot image classification that explores applying data augmentations in the frozen feature space, dubbed 'frozen feature augmentation (FroFA)', covering twenty augmentations in total. Our study demonstrates that adopting a deceptively simple pointwise FroFA, such as brightness, can improve few-shot performance consistently across three network architectures, three large pretraining datasets, and eight transfer datasets.