# Exemplar-Based Contrastive Self-Supervised Learning with Few-Shot Class Incremental Learning

arXiv: https://arxiv.org/abs/2202.02601 · HTML: https://mlsanity.com/paper/2202.02601/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 10 references that are in the map.
- First posted on arXiv 5 Feb 2022.

## Builds on (most cited first, 8 of 8)

- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2104.14548/) (2021)
- [Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2004.10956/) (2020)
- [Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuning](https://mlsanity.com/paper/2003.12862/) (2020)
- [Boosting Few-Shot Visual Learning with Self-Supervision](https://mlsanity.com/paper/1906.05186/) (2019)
- [Neighborhood Contrastive Learning for Novel Class Discovery](https://mlsanity.com/paper/2106.10731/) (2021)
- [Concept-Oriented Deep Learning](https://mlsanity.com/paper/1806.01756/) (2018)
- [Concept Representation Learning with Contrastive Self-Supervised Learning](https://mlsanity.com/paper/2112.05677/) (2021)

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

- [Dual Embodied-Symbolic Concept Representations for Deep Learning](https://mlsanity.com/paper/2203.00600/) (2022)
- [Embodied-Symbolic Contrastive Graph Self-Supervised Learning for Molecular Graphs](https://mlsanity.com/paper/2205.06783/) (2022)

## Abstract (arXiv)

Humans are capable of learning new concepts from only a few (labeled) exemplars, incrementally and continually. This happens within the context that we can differentiate among the exemplars, and between the exemplars and large amounts of other data (unlabeled and labeled). This suggests, in human learning, supervised learning of concepts based on exemplars takes place within the larger context of contrastive self-supervised learning (CSSL) based on unlabeled and labeled data. We discuss extending CSSL (1) to be based mainly on exemplars and only secondly on data augmentation, and (2) to apply to both unlabeled data (a large amount is available in general) and labeled data (a few exemplars can be obtained with valuable supervised knowledge). A major benefit of the extensions is that exemplar-based CSSL, with supervised finetuning, supports few-shot class incremental learning (CIL). Specifically, we discuss exemplar-based CSSL including: nearest-neighbor CSSL, neighborhood CSSL with supervised pretraining, and exemplar CSSL with supervised finetuning. We further discuss using exemplar-based CSSL to facilitate few-shot learning and, in particular, few-shot CIL.