# Calibrating Higher-Order Statistics for Few-Shot Class-Incremental Learning with Pre-trained Vision Transformers

arXiv: https://arxiv.org/abs/2404.06622 · HTML: https://mlsanity.com/paper/2404.06622/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 62 references that are in the map.
- First posted on arXiv 9 Apr 2024.

## Builds on (most cited first, 30 of 45)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [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 Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [Three scenarios for continual learning](https://mlsanity.com/paper/1904.07734/) (2019)
- [ImageNet-21K Pretraining for the Masses](https://mlsanity.com/paper/2104.10972/) (2021)
- [Class-incremental learning: survey and performance evaluation on image classification](https://mlsanity.com/paper/2010.15277/) (2020)
- [Measuring Catastrophic Forgetting in Neural Networks](https://mlsanity.com/paper/1708.02072/) (2017)
- [Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2004.10956/) (2020)
- [Learning without Memorizing](https://mlsanity.com/paper/1811.08051/) (2018)
- [Few-Shot Incremental Learning with Continually Evolved Classifiers](https://mlsanity.com/paper/2104.03047/) (2021)
- [Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need](https://mlsanity.com/paper/2303.07338/) (2023)
- [SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model](https://mlsanity.com/paper/2303.05118/) (2023)
- [Free Lunch for Few-shot Learning: Distribution Calibration](https://mlsanity.com/paper/2101.06395/) (2021)
- [RanPAC: Random Projections and Pre-trained Models for Continual Learning](https://mlsanity.com/paper/2307.02251/) (2023)
- [Continual Learning with Pre-Trained Models: A Survey](https://mlsanity.com/paper/2401.16386/) (2024)
- [Continual Prototype Evolution: Learning Online from Non-Stationary Data Streams](https://mlsanity.com/paper/2009.00919/) (2020)
- [Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting](https://mlsanity.com/paper/1802.02950/) (2018)
- [Forward Compatible Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2203.06953/) (2022)
- [FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learning](https://mlsanity.com/paper/2211.13131/) (2022)
- [Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learning](https://mlsanity.com/paper/2302.03004/) (2023)
- [Constrained Few-shot Class-incremental Learning](https://mlsanity.com/paper/2203.16588/) (2022)
- [Lifelong Machine Learning with Deep Streaming Linear Discriminant Analysis](https://mlsanity.com/paper/1909.01520/) (2019)
- [Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks](https://mlsanity.com/paper/2203.17030/) (2022)

## Built on by (most cited first, 9 of 9)

- [Exemplar-free Continual Representation Learning via Learnable Drift Compensation](https://mlsanity.com/paper/2407.08536/) (2024)
- [Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2407.06136/) (2024)
- [Covariances for Free: Exploiting Mean Distributions for Training-free Federated Learning](https://mlsanity.com/paper/2412.14326/) (2024)
- [Efficient Few-Shot Continual Learning in Vision-Language Models](https://mlsanity.com/paper/2502.04098/) (2025)
- [DSS-Prompt: Dynamic-Static Synergistic Prompting for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2508.09785/) (2025)
- [Continuous Knowledge-Preserving Decomposition with Adaptive Layer Selection for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2501.05017/) (2025)
- [Consistency-Driven Calibration and Matching for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2506.19558/) (2025)
- [HyCal: A Training-Free Prototype Calibration Method for Cross-Discipline Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2604.15678/) (2026)
- [Brain-inspired analogical mixture prototypes for few-shot class-incremental learning](https://mlsanity.com/paper/2502.18923/) (2025)

## Abstract (arXiv)

Few-shot class-incremental learning (FSCIL) aims to adapt the model to new classes from very few data (5 samples) without forgetting the previously learned classes. Recent works in many-shot CIL (MSCIL) (using all available training data) exploited pre-trained models to reduce forgetting and achieve better plasticity. In a similar fashion, we use ViT models pre-trained on large-scale datasets for few-shot settings, which face the critical issue of low plasticity. FSCIL methods start with a many-shot first task to learn a very good feature extractor and then move to the few-shot setting from the second task onwards. While the focus of most recent studies is on how to learn the many-shot first task so that the model generalizes to all future few-shot tasks, we explore in this work how to better model the few-shot data using pre-trained models, irrespective of how the first task is trained. Inspired by recent works in MSCIL, we explore how using higher-order feature statistics can influence the classification of few-shot classes. We identify the main challenge of obtaining a good covariance matrix from few-shot data and propose to calibrate the covariance matrix for new classes based on semantic similarity to the many-shot base classes. Using the calibrated feature statistics in combination with existing methods significantly improves few-shot continual classification on several FSCIL benchmarks. Code is available at https://github.com/dipamgoswami/FSCIL-Calibration.