# Data-Free Class-Incremental Gesture Recognition with Prototype-Guided Pseudo Feature Replay

arXiv: https://arxiv.org/abs/2505.20049 · HTML: https://mlsanity.com/paper/2505.20049/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 47 references that are in the map.
- First posted on arXiv 26 May 2025.

## Builds on (most cited first, 24 of 24)

- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [Decoupling Representation and Classifier for Long-Tailed Recognition](https://mlsanity.com/paper/1910.09217/) (2019)
- [Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion](https://mlsanity.com/paper/1912.08795/) (2019)
- [Learning without Memorizing](https://mlsanity.com/paper/1811.08051/) (2018)
- [MediaPipe Hands: On-device Real-time Hand Tracking](https://mlsanity.com/paper/2006.10214/) (2020)
- [Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning](https://mlsanity.com/paper/2106.09701/) (2021)
- [FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learning](https://mlsanity.com/paper/2211.13131/) (2022)
- [Self-Sustaining Representation Expansion for Non-Exemplar Class-Incremental Learning](https://mlsanity.com/paper/2203.06359/) (2022)
- [Generative Feature Replay For Class-Incremental Learning](https://mlsanity.com/paper/2004.09199/) (2020)
- [Encoder Based Lifelong Learning](https://mlsanity.com/paper/1704.01920/) (2017)
- [GAN Memory with No Forgetting](https://mlsanity.com/paper/2006.07543/) (2020)
- [R-DFCIL: Relation-Guided Representation Learning for Data-Free Class Incremental Learning](https://mlsanity.com/paper/2203.13104/) (2022)
- [A neural network based on SPD manifold learning for skeleton-based hand gesture recognition](https://mlsanity.com/paper/1904.12970/) (2019)
- [Create Your World: Lifelong Text-to-Image Diffusion](https://mlsanity.com/paper/2309.04430/) (2023)
- [Searching Multi-Rate and Multi-Modal Temporal Enhanced Networks for Gesture Recognition](https://mlsanity.com/paper/2008.09412/) (2020)
- [Real-time Hand Gesture Detection and Classification Using Convolutional Neural Networks](https://mlsanity.com/paper/1901.10323/) (2019)
- [Construct Dynamic Graphs for Hand Gesture Recognition via Spatial-Temporal Attention](https://mlsanity.com/paper/1907.08871/) (2019)
- [Res3ATN -- Deep 3D Residual Attention Network for Hand Gesture Recognition in Videos](https://mlsanity.com/paper/2001.01083/) (2020)
- [MuseumMaker: Continual Style Customization without Catastrophic Forgetting](https://mlsanity.com/paper/2404.16612/) (2024)
- [3D Hand Pose and Shape Estimation from RGB Images for Keypoint-Based Hand Gesture Recognition](https://mlsanity.com/paper/2109.13879/) (2021)
- [Representative Task Self-selection for Flexible Clustered Lifelong Learning](https://mlsanity.com/paper/1903.02173/) (2019)
- [Rethinking Classifier Re-Training in Long-Tailed Recognition: A Simple Logits Retargeting Approach](https://mlsanity.com/paper/2403.00250/) (2024)

## Built on by (most cited first, 2 of 2)

- [Virtual Category-Guided Continual Generalized Category Discovery](https://mlsanity.com/paper/2607.04984/) (2026)
- [Zero-Shot Skeleton-Based Action Anticipation](https://mlsanity.com/paper/2608.14243/) (2026)

## Abstract (arXiv)

Gesture recognition is an important research area in the field of computer vision. Most gesture recognition efforts focus on close-set scenarios, thereby limiting the capacity to effectively handle unseen or novel gestures. We aim to address class-incremental gesture recognition, which entails the ability to accommodate new and previously unseen gestures over time. Specifically, we introduce a Prototype-Guided Pseudo Feature Replay (PGPFR) framework for data-free class-incremental gesture recognition. This framework comprises four components: Pseudo Feature Generation with Batch Prototypes (PFGBP), Variational Prototype Replay (VPR) for old classes, Truncated Cross-Entropy (TCE) for new classes, and Continual Classifier Re-Training (CCRT). To tackle the issue of catastrophic forgetting, the PFGBP dynamically generates a diversity of pseudo features in an online manner, leveraging class prototypes of old classes along with batch class prototypes of new classes. Furthermore, the VPR enforces consistency between the classifier's weights and the prototypes of old classes, leveraging class prototypes and covariance matrices to enhance robustness and generalization capabilities. The TCE mitigates the impact of domain differences of the classifier caused by pseudo features. Finally, the CCRT training strategy is designed to prevent overfitting to new classes and ensure the stability of features extracted from old classes. Extensive experiments conducted on two widely used gesture recognition datasets, namely SHREC 2017 3D and EgoGesture 3D, demonstrate that our approach outperforms existing state-of-the-art methods by 11.8% and 12.8% in terms of mean global accuracy, respectively. The code is available on https://github.com/sunao-101/PGPFR-3/.