# XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot Learning

arXiv: https://arxiv.org/abs/2003.08561 · HTML: https://mlsanity.com/paper/2003.08561/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Mar 2020.

## Built on by (most cited first, 30 of 31)

- [Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learning](https://mlsanity.com/paper/2302.03004/) (2023)
- [Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2103.04059/) (2021)
- [Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks](https://mlsanity.com/paper/2203.17030/) (2022)
- [A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning](https://mlsanity.com/paper/2307.09218/) (2023)
- [Subspace Regularizers for Few-Shot Class Incremental Learning](https://mlsanity.com/paper/2110.07059/) (2021)
- [Recent Advances of Continual Learning in Computer Vision: An Overview](https://mlsanity.com/paper/2109.11369/) (2021)
- [A Survey on Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2304.08130/) (2023)
- [Graph Few-shot Class-incremental Learning](https://mlsanity.com/paper/2112.12819/) (2021)
- [Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developments](https://mlsanity.com/paper/2105.08149/) (2021)
- [SAFE: Slow and Fast Parameter-Efficient Tuning for Continual Learning with Pre-Trained Models](https://mlsanity.com/paper/2411.02175/) (2024)
- [Incremental Few-Shot Semantic Segmentation via Embedding Adaptive-Update and Hyper-class Representation](https://mlsanity.com/paper/2207.12964/) (2022)
- [Neural Collapse Terminus: A Unified Solution for Class Incremental Learning and Its Variants](https://mlsanity.com/paper/2308.01746/) (2023)
- [Learnable Distribution Calibration for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2210.00232/) (2022)
- [Learnable Expansion-and-Compression Network for Few-shot Class-Incremental Learning](https://mlsanity.com/paper/2104.02281/) (2021)
- [Meta Learning on a Sequence of Imbalanced Domains with Difficulty Awareness](https://mlsanity.com/paper/2109.14120/) (2021)
- [RankDNN: Learning to Rank for Few-shot Learning](https://mlsanity.com/paper/2211.15320/) (2022)
- [Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2407.06136/) (2024)
- [Latest Advancements Towards Catastrophic Forgetting under Data Scarcity: A Comprehensive Survey on Few-Shot Class Incremental Learning](https://mlsanity.com/paper/2502.08181/) (2025)
- [Incremental Meta-Learning via Episodic Replay Distillation for Few-Shot Image Recognition](https://mlsanity.com/paper/2111.04993/) (2021)
- [Better Generalized Few-Shot Learning Even Without Base Data](https://mlsanity.com/paper/2211.16095/) (2022)
- [Meta-free few-shot learning via representation learning with weight averaging](https://mlsanity.com/paper/2204.12466/) (2022)
- [Lifelong DP: Consistently Bounded Differential Privacy in Lifelong Machine Learning](https://mlsanity.com/paper/2207.12831/) (2022)
- [Unsupervised Few-shot Learning via Deep Laplacian Eigenmaps](https://mlsanity.com/paper/2210.03595/) (2022)
- [A Strong Baseline for Semi-Supervised Incremental Few-Shot Learning](https://mlsanity.com/paper/2110.11128/) (2021)
- [Clustering Enabled Few-Shot Load Forecasting](https://mlsanity.com/paper/2202.07939/) (2022)
- [Variational Autoencoder with Disentanglement Priors for Low-Resource Task-Specific Natural Language Generation](https://mlsanity.com/paper/2202.13363/) (2022)
- [Continuous Knowledge-Preserving Decomposition with Adaptive Layer Selection for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2501.05017/) (2025)
- [Few-shot Incremental Event Detection](https://mlsanity.com/paper/2209.01979/) (2022)
- [Expanding continual few-shot learning benchmarks to include recognition of specific instances](https://mlsanity.com/paper/2209.07863/) (2022)
- [Few Shot Class Incremental Learning using Vision-Language models](https://mlsanity.com/paper/2405.01040/) (2024)

## Abstract (arXiv)

Learning novel concepts while preserving prior knowledge is a long-standing challenge in machine learning. The challenge gets greater when a novel task is given with only a few labeled examples, a problem known as incremental few-shot learning. We propose XtarNet, which learns to extract task-adaptive representation (TAR) for facilitating incremental few-shot learning. The method utilizes a backbone network pretrained on a set of base categories while also employing additional modules that are meta-trained across episodes. Given a new task, the novel feature extracted from the meta-trained modules is mixed with the base feature obtained from the pretrained model. The process of combining two different features provides TAR and is also controlled by meta-trained modules. The TAR contains effective information for classifying both novel and base categories. The base and novel classifiers quickly adapt to a given task by utilizing the TAR. Experiments on standard image datasets indicate that XtarNet achieves state-of-the-art incremental few-shot learning performance. The concept of TAR can also be used in conjunction with existing incremental few-shot learning methods; extensive simulation results in fact show that applying TAR enhances the known methods significantly.