# FeTrIL++: Feature Translation for Exemplar-Free Class-Incremental Learning with Hill-Climbing

arXiv: https://arxiv.org/abs/2403.07406 · HTML: https://mlsanity.com/paper/2403.07406/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 24 references that are in the map.
- First posted on arXiv 12 Mar 2024.

## Builds on (most cited first, 15 of 15)

- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Large Scale Incremental Learning](https://mlsanity.com/paper/1905.13260/) (2019)
- [Class-incremental learning: survey and performance evaluation on image classification](https://mlsanity.com/paper/2010.15277/) (2020)
- [Semantic Drift Compensation for Class-Incremental Learning](https://mlsanity.com/paper/2004.00440/) (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)
- [Lifelong Machine Learning with Deep Streaming Linear Discriminant Analysis](https://mlsanity.com/paper/1909.01520/) (2019)
- [Efficient Feature Transformations for Discriminative and Generative Continual Learning](https://mlsanity.com/paper/2103.13558/) (2021)
- [Online Continual Learning for Embedded Devices](https://mlsanity.com/paper/2203.10681/) (2022)
- [A TinyML Platform for On-Device Continual Learning with Quantized Latent Replays](https://mlsanity.com/paper/2110.10486/) (2021)
- [DeeSIL: Deep-Shallow Incremental Learning](https://mlsanity.com/paper/1808.06396/) (2018)
- [Balanced softmax cross-entropy for incremental learning with and without memory](https://mlsanity.com/paper/2103.12532/) (2021)
- [Dataset Knowledge Transfer for Class-Incremental Learning without Memory](https://mlsanity.com/paper/2110.08421/) (2021)

## Built on by (most cited first, 5 of 5)

- [The ethical situation of DALL-E 2](https://mlsanity.com/paper/2405.19176/) (2024)
- [Enhanced Anomaly Detection in Automotive Systems Using SAAD: Statistical Aggregated Anomaly Detection](https://mlsanity.com/paper/2406.08516/) (2024)
- [Sisteme Hibride de Invatare Automata si Aplicatii](https://mlsanity.com/paper/2406.11870/) (2024)
- [An experimental approach on Few Shot Class Incremental Learning](https://mlsanity.com/paper/2503.11349/) (2025)
- [CI-CBM: Class-Incremental Concept Bottleneck Model for Interpretable Continual Learning](https://mlsanity.com/paper/2604.14519/) (2026)

## Abstract (arXiv)

Exemplar-free class-incremental learning (EFCIL) poses significant challenges, primarily due to catastrophic forgetting, necessitating a delicate balance between stability and plasticity to accurately recognize both new and previous classes. Traditional EFCIL approaches typically skew towards either model plasticity through successive fine-tuning or stability by employing a fixed feature extractor beyond the initial incremental state. Building upon the foundational FeTrIL framework, our research extends into novel experimental domains to examine the efficacy of various oversampling techniques and dynamic optimization strategies across multiple challenging datasets and incremental settings. We specifically explore how oversampling impacts accuracy relative to feature availability and how different optimization methodologies, including dynamic recalibration and feature pool diversification, influence incremental learning outcomes. The results from these comprehensive experiments, conducted on CIFAR100, Tiny-ImageNet, and an ImageNet-Subset, under-score the superior performance of FeTrIL in balancing accuracy for both new and past classes against ten contemporary methods. Notably, our extensions reveal the nuanced impacts of oversampling and optimization on EFCIL, contributing to a more refined understanding of feature-space manipulation for class incremental learning. FeTrIL and its extended analysis in this paper FeTrIL++ pave the way for more adaptable and efficient EFCIL methodologies, promising significant improvements in handling catastrophic forgetting without the need for exemplars.