# Incremental Few-Shot Learning via Implanting and Compressing

arXiv: https://arxiv.org/abs/2203.10297 · HTML: https://mlsanity.com/paper/2203.10297/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 42 references that are in the map.
- First posted on arXiv 19 Mar 2022.

## Builds on (most cited first, 30 of 34)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [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)
- [On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima](https://mlsanity.com/paper/1609.04836/) (2016)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence](https://mlsanity.com/paper/1801.10112/) (2018)
- [Overcoming catastrophic forgetting with hard attention to the task](https://mlsanity.com/paper/1801.01423/) (2018)
- [End-to-End Incremental Learning](https://mlsanity.com/paper/1807.09536/) (2018)
- [Towards Open Set Deep Networks](https://mlsanity.com/paper/1511.06233/) (2015)
- [Class-incremental learning: survey and performance evaluation on image classification](https://mlsanity.com/paper/2010.15277/) (2020)
- [Dynamic Few-Shot Visual Learning without Forgetting](https://mlsanity.com/paper/1804.09458/) (2018)
- [Towards Open World Object Detection](https://mlsanity.com/paper/2103.02603/) (2021)
- [SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization](https://mlsanity.com/paper/1911.03437/) (2019)
- [Overcoming Catastrophic Forgetting by Incremental Moment Matching](https://mlsanity.com/paper/1703.08475/) (2017)
- [Towards Open World Recognition](https://mlsanity.com/paper/1412.5687/) (2014)
- [Incremental Learning of Object Detectors without Catastrophic Forgetting](https://mlsanity.com/paper/1708.06977/) (2017)
- [Meta R-CNN : Towards General Solver for Instance-level Few-shot Learning](https://mlsanity.com/paper/1909.13032/) (2019)
- [FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding](https://mlsanity.com/paper/2103.05950/) (2021)
- [Generative OpenMax for Multi-Class Open Set Classification](https://mlsanity.com/paper/1707.07418/) (2017)
- [Better Fine-Tuning by Reducing Representational Collapse](https://mlsanity.com/paper/2008.03156/) (2020)
- [Incremental Few-Shot Object Detection](https://mlsanity.com/paper/2003.04668/) (2020)
- [Analyzing and Improving Representations with the Soft Nearest Neighbor Loss](https://mlsanity.com/paper/1902.01889/) (2019)
- [Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection](https://mlsanity.com/paper/2103.04612/) (2021)
- [Hallucination Improves Few-Shot Object Detection](https://mlsanity.com/paper/2105.01294/) (2021)
- [Incremental Few-Shot Instance Segmentation](https://mlsanity.com/paper/2105.05312/) (2021)
- [Distance-Based Regularisation of Deep Networks for Fine-Tuning](https://mlsanity.com/paper/2002.08253/) (2020)

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

- [Masked Self-Supervision for Remaining Useful Lifetime Prediction in Machine Tools](https://mlsanity.com/paper/2207.01219/) (2022)
- [CAM/CAD Point Cloud Part Segmentation via Few-Shot Learning](https://mlsanity.com/paper/2207.01218/) (2022)

## Abstract (arXiv)

This work focuses on tackling the challenging but realistic visual task of Incremental Few-Shot Learning (IFSL), which requires a model to continually learn novel classes from only a few examples while not forgetting the base classes on which it was pre-trained. Our study reveals that the challenges of IFSL lie in both inter-class separation and novel-class representation. Dur to intra-class variation, a novel class may implicitly leverage the knowledge from multiple base classes to construct its feature representation. Hence, simply reusing the pre-trained embedding space could lead to a scattered feature distribution and result in category confusion. To address such issues, we propose a two-step learning strategy referred to as Implanting and Compressing (IMCO), which optimizes both feature space partition and novel class reconstruction in a systematic manner. Specifically, in the Implanting step, we propose to mimic the data distribution of novel classes with the assistance of data-abundant base set, so that a model could learn semantically-rich features that are beneficial for discriminating between the base and other unseen classes. In the Compressing step, we adapt the feature extractor to precisely represent each novel class for enhancing intra-class compactness, together with a regularized parameter updating rule for preventing aggressive model updating. Finally, we demonstrate that IMCO outperforms competing baselines with a significant margin, both in image classification task and more challenging object detection task.