# Online Continual Learning for Robust Indoor Object Recognition

arXiv: https://arxiv.org/abs/2307.09827 · HTML: https://mlsanity.com/paper/2307.09827/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 70 references that are in the map.
- First posted on arXiv 19 Jul 2023.

## Builds on (most cited first, 30 of 47)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [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)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Certified Adversarial Robustness via Randomized Smoothing](https://mlsanity.com/paper/1902.02918/) (2019)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence](https://mlsanity.com/paper/1801.10112/) (2018)
- [Deep Visual Domain Adaptation: A Survey](https://mlsanity.com/paper/1802.03601/) (2018)
- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [MEMO: Test Time Robustness via Adaptation and Augmentation](https://mlsanity.com/paper/2110.09506/) (2021)
- [Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks](https://mlsanity.com/paper/1807.07356/) (2018)
- [Online Continual Learning in Image Classification: An Empirical Survey](https://mlsanity.com/paper/2101.10423/) (2021)
- [Supervised Contrastive Replay: Revisiting the Nearest Class Mean Classifier in Online Class-Incremental Continual Learning](https://mlsanity.com/paper/2103.13885/) (2021)
- [Memory Efficient Experience Replay for Streaming Learning](https://mlsanity.com/paper/1809.05922/) (2018)
- [Better Aggregation in Test-Time Augmentation](https://mlsanity.com/paper/2011.11156/) (2020)
- [Test-Time Adaptation via Conjugate Pseudo-labels](https://mlsanity.com/paper/2207.09640/) (2022)
- [Latent Replay for Real-Time Continual Learning](https://mlsanity.com/paper/1912.01100/) (2019)
- [Lifelong Machine Learning with Deep Streaming Linear Discriminant Analysis](https://mlsanity.com/paper/1909.01520/) (2019)
- [Unsupervised Domain Adaptation in Semantic Segmentation: a Review](https://mlsanity.com/paper/2005.10876/) (2020)
- [Towards Faster Training of Global Covariance Pooling Networks by Iterative Matrix Square Root Normalization](https://mlsanity.com/paper/1712.01034/) (2017)
- [Few-Shot Lifelong Learning](https://mlsanity.com/paper/2103.00991/) (2021)
- [Learning Loss for Test-Time Augmentation](https://mlsanity.com/paper/2010.11422/) (2020)
- [Online Continual Learning for Embedded Devices](https://mlsanity.com/paper/2203.10681/) (2022)
- [Stochastic Pooling for Regularization of Deep Convolutional Neural Networks](https://mlsanity.com/paper/1301.3557/) (2013)

## Built on by (most cited first, 9 of 9)

- [Deep Policy Gradient Methods Without Batch Updates, Target Networks, or Replay Buffers](https://mlsanity.com/paper/2411.15370/) (2024)
- [Continual Learning for Autonomous Robots: A Prototype-based Approach](https://mlsanity.com/paper/2404.00418/) (2024)
- [Cross-Architecture Auxiliary Feature Space Translation for Efficient Few-Shot Personalized Object Detection](https://mlsanity.com/paper/2407.01193/) (2024)
- [HOP to the Next Tasks and Domains for Continual Learning in NLP](https://mlsanity.com/paper/2402.18449/) (2024)
- [Swiss DINO: Efficient and Versatile Vision Framework for On-device Personal Object Search](https://mlsanity.com/paper/2407.07541/) (2024)
- [A Modular System for Enhanced Robustness of Multimedia Understanding Networks via Deep Parametric Estimation](https://mlsanity.com/paper/2402.18402/) (2024)
- [Object-conditioned Bag of Instances for Few-Shot Personalized Instance Recognition](https://mlsanity.com/paper/2404.01397/) (2024)
- [Enhanced Model Robustness to Input Corruptions by Per-corruption Adaptation of Normalization Statistics](https://mlsanity.com/paper/2407.06450/) (2024)
- [Controllable Forgetting Mechanism for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2501.15998/) (2025)

## Abstract (arXiv)

Vision systems mounted on home robots need to interact with unseen classes in changing environments. Robots have limited computational resources, labelled data and storage capability. These requirements pose some unique challenges: models should adapt without forgetting past knowledge in a data- and parameter-efficient way. We characterize the problem as few-shot (FS) online continual learning (OCL), where robotic agents learn from a non-repeated stream of few-shot data updating only a few model parameters. Additionally, such models experience variable conditions at test time, where objects may appear in different poses (e.g., horizontal or vertical) and environments (e.g., day or night). To improve robustness of CL agents, we propose RobOCLe, which; 1) constructs an enriched feature space computing high order statistical moments from the embedded features of samples; and 2) computes similarity between high order statistics of the samples on the enriched feature space, and predicts their class labels. We evaluate robustness of CL models to train/test augmentations in various cases. We show that different moments allow RobOCLe to capture different properties of deformations, providing higher robustness with no decrease of inference speed.