# Unsupervised Online Learning for Robotic Interestingness with Visual Memory

arXiv: https://arxiv.org/abs/2111.09793 · HTML: https://mlsanity.com/paper/2111.09793/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 57 references that are in the map.
- First posted on arXiv 18 Nov 2021.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [Neural Turing Machines](https://mlsanity.com/paper/1410.5401/) (2014)
- [Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection](https://mlsanity.com/paper/1904.02639/) (2019)
- [Future Frame Prediction for Anomaly Detection -- A New Baseline](https://mlsanity.com/paper/1712.09867/) (2017)
- [Learning Temporal Regularity in Video Sequences](https://mlsanity.com/paper/1604.04574/) (2016)
- [Latent Space Autoregression for Novelty Detection](https://mlsanity.com/paper/1807.01653/) (2018)
- [PCAN: 3D Attention Map Learning Using Contextual Information for Point Cloud Based Retrieval](https://mlsanity.com/paper/1904.09793/) (2019)
- [Learning Uncertain Convolutional Features for Accurate Saliency Detection](https://mlsanity.com/paper/1708.02031/) (2017)
- [Kervolutional Neural Networks](https://mlsanity.com/paper/1904.03955/) (2019)
- [Robust Subjective Visual Property Prediction from Crowdsourced Pairwise Labels](https://mlsanity.com/paper/1501.06202/) (2015)
- [Kernel Cross-Correlator](https://mlsanity.com/paper/1709.05936/) (2017)
- [Memorization Precedes Generation: Learning Unsupervised GANs with Memory Networks](https://mlsanity.com/paper/1803.01500/) (2018)
- [Visual Memorability for Robotic Interestingness via Unsupervised Online Learning](https://mlsanity.com/paper/2005.08829/) (2020)
- [Improved Generalization of Heading Direction Estimation for Aerial Filming Using Semi-supervised Regression](https://mlsanity.com/paper/1903.11174/) (2019)

## Built on by (most cited first, 5 of 5)

- [Imperative Learning: A Self-supervised Neuro-Symbolic Learning Framework for Robot Autonomy](https://mlsanity.com/paper/2406.16087/) (2024)
- [AirDet: Few-Shot Detection without Fine-tuning for Autonomous Exploration](https://mlsanity.com/paper/2112.01740/) (2021)
- [AirShot: Efficient Few-Shot Detection for Autonomous Exploration](https://mlsanity.com/paper/2404.05069/) (2024)
- [AirObject: A Temporally Evolving Graph Embedding for Object Identification](https://mlsanity.com/paper/2111.15150/) (2021)
- [Vision-Language Memory for Spatial Reasoning](https://mlsanity.com/paper/2511.20644/) (2025)

## Abstract (arXiv)

Autonomous robots frequently need to detect "interesting" scenes to decide on further exploration, or to decide which data to share for cooperation. These scenarios often require fast deployment with little or no training data. Prior work considers "interestingness" based on data from the same distribution. Instead, we propose to develop a method that automatically adapts online to the environment to report interesting scenes quickly. To address this problem, we develop a novel translation-invariant visual memory and design a three-stage architecture for long-term, short-term, and online learning, which enables the system to learn human-like experience, environmental knowledge, and online adaption, respectively. With this system, we achieve an average of 20% higher accuracy than the state-of-the-art unsupervised methods in a subterranean tunnel environment. We show comparable performance to supervised methods for robot exploration scenarios showing the efficacy of our approach. We expect that the presented method will play an important role in the robotic interestingness recognition exploration tasks.