# Wandering Within a World: Online Contextualized Few-Shot Learning

arXiv: https://arxiv.org/abs/2007.04546 · HTML: https://mlsanity.com/paper/2007.04546/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jul 2020.

## Built on by (most cited first, 22 of 22)

- ["This is my unicorn, Fluffy": Personalizing frozen vision-language representations](https://mlsanity.com/paper/2204.01694/) (2022)
- [Recent Advances of Continual Learning in Computer Vision: An Overview](https://mlsanity.com/paper/2109.11369/) (2021)
- [Meta-Learning Online Adaptation of Language Models](https://mlsanity.com/paper/2305.15076/) (2023)
- [Strong Baselines for Parameter Efficient Few-Shot Fine-tuning](https://mlsanity.com/paper/2304.01917/) (2023)
- [Wanderlust: Online Continual Object Detection in the Real World](https://mlsanity.com/paper/2108.11005/) (2021)
- [Memory-Efficient Semi-Supervised Continual Learning: The World is its Own Replay Buffer](https://mlsanity.com/paper/2101.09536/) (2021)
- [Which images to label for few-shot medical landmark detection?](https://mlsanity.com/paper/2112.04386/) (2021)
- [When Meta-Learning Meets Online and Continual Learning: A Survey](https://mlsanity.com/paper/2311.05241/) (2023)
- [Visual Data-Type Understanding does not emerge from Scaling Vision-Language Models](https://mlsanity.com/paper/2310.08577/) (2023)
- [ViLCo-Bench: VIdeo Language COntinual learning Benchmark](https://mlsanity.com/paper/2406.13123/) (2024)
- [Bayesian Embeddings for Few-Shot Open World Recognition](https://mlsanity.com/paper/2107.13682/) (2021)
- [Lifelong Adaptive Machine Learning for Sensor-based Human Activity Recognition Using Prototypical Networks](https://mlsanity.com/paper/2203.05692/) (2022)
- [Reawakening knowledge: Anticipatory recovery from catastrophic interference via structured training](https://mlsanity.com/paper/2403.09613/) (2024)
- [Contextualizing Meta-Learning via Learning to Decompose](https://mlsanity.com/paper/2106.08112/) (2021)
- [Continual Learning for Autonomous Robots: A Prototype-based Approach](https://mlsanity.com/paper/2404.00418/) (2024)
- [Online Unsupervised Learning of Visual Representations and Categories](https://mlsanity.com/paper/2109.05675/) (2021)
- [CoLLEGe: Concept Embedding Generation for Large Language Models](https://mlsanity.com/paper/2403.15362/) (2024)
- [Lifelong Wandering: A realistic few-shot online continual learning setting](https://mlsanity.com/paper/2206.07932/) (2022)
- [Expanding continual few-shot learning benchmarks to include recognition of specific instances](https://mlsanity.com/paper/2209.07863/) (2022)
- [Active Class Selection for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2307.02641/) (2023)
- [Continual Improvement of Threshold-Based Novelty Detection](https://mlsanity.com/paper/2309.02551/) (2023)
- [Online Continual Learning on Intel Loihi 2 via a Co-designed Spiking Neural Network](https://mlsanity.com/paper/2511.01553/) (2025)

## Abstract (arXiv)

We aim to bridge the gap between typical human and machine-learning environments by extending the standard framework of few-shot learning to an online, continual setting. In this setting, episodes do not have separate training and testing phases, and instead models are evaluated online while learning novel classes. As in the real world, where the presence of spatiotemporal context helps us retrieve learned skills in the past, our online few-shot learning setting also features an underlying context that changes throughout time. Object classes are correlated within a context and inferring the correct context can lead to better performance. Building upon this setting, we propose a new few-shot learning dataset based on large scale indoor imagery that mimics the visual experience of an agent wandering within a world. Furthermore, we convert popular few-shot learning approaches into online versions and we also propose a new contextual prototypical memory model that can make use of spatiotemporal contextual information from the recent past.