# Self-supervised Representation Learning for Reliable Robotic Monitoring of Fruit Anomalies

arXiv: https://arxiv.org/abs/2109.10135 · HTML: https://mlsanity.com/paper/2109.10135/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 34 references that are in the map.
- First posted on arXiv 21 Sep 2021.

## Builds on (most cited first, 15 of 15)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [CutPaste: Self-Supervised Learning for Anomaly Detection and Localization](https://mlsanity.com/paper/2104.04015/) (2021)
- [Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty](https://mlsanity.com/paper/1906.12340/) (2019)
- [Revisiting Self-Supervised Visual Representation Learning](https://mlsanity.com/paper/1901.09005/) (2019)
- [Unsupervised Representation Learning by Sorting Sequences](https://mlsanity.com/paper/1708.01246/) (2017)
- [Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentation](https://mlsanity.com/paper/2006.16067/) (2020)
- [Adversarially Learned One-Class Classifier for Novelty Detection](https://mlsanity.com/paper/1802.09088/) (2018)
- [OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representations](https://mlsanity.com/paper/1903.08550/) (2019)
- [Colorization as a Proxy Task for Visual Understanding](https://mlsanity.com/paper/1703.04044/) (2017)
- [Tracking Emerges by Colorizing Videos](https://mlsanity.com/paper/1806.09594/) (2018)
- [Modeling the Distribution of Normal Data in Pre-Trained Deep Features for Anomaly Detection](https://mlsanity.com/paper/2005.14140/) (2020)
- [Learning Deep Features for One-Class Classification](https://mlsanity.com/paper/1801.05365/) (2018)
- [Identification of Abnormal States in Videos of Ants Undergoing Social Phase Change](https://mlsanity.com/paper/2009.08626/) (2020)

## Built on by (most cited first, 6 of 6)

- [Self-supervised On-device Federated Learning from Unlabeled Streams](https://mlsanity.com/paper/2212.01006/) (2022)
- [INoD: Injected Noise Discriminator for Self-Supervised Representation Learning in Agricultural Fields](https://mlsanity.com/paper/2303.18101/) (2023)
- [OLGA: One-cLass Graph Autoencoder](https://mlsanity.com/paper/2406.09131/) (2024)
- [Synthetic Data Generation for Anomaly Detection on Table Grapes](https://mlsanity.com/paper/2412.12949/) (2024)
- [Towards Fully Automated Decision-Making Systems for Greenhouse Control: Challenges and Opportunities](https://mlsanity.com/paper/2503.21640/) (2025)
- [CA-Cut: Crop-Aligned Cutout for Data Augmentation to Learn More Robust Under-Canopy Navigation](https://mlsanity.com/paper/2507.17727/) (2025)

## Abstract (arXiv)

Data augmentation can be a simple yet powerful tool for autonomous robots to fully utilise available data for selfsupervised identification of atypical scenes or objects. State-of-the-art augmentation methods arbitrarily embed "structural" peculiarity on typical images so that classifying these artefacts can provide guidance for learning representations for the detection of anomalous visual signals. In this paper, however, we argue that learning such structure-sensitive representations can be a suboptimal approach to some classes of anomaly (e.g., unhealthy fruits) which could be better recognised by a different type of visual element such as "colour". We thus propose Channel Randomisation as a novel data augmentation method for restricting neural networks to learn encoding of "colour irregularity" whilst predicting channel-randomised images to ultimately build reliable fruit-monitoring robots identifying atypical fruit qualities. Our experiments show that (1) this colour-based alternative can better learn representations for consistently accurate identification of fruit anomalies in various fruit species, and also, (2) unlike other methods, the validation accuracy can be utilised as a criterion for early stopping of training in practice due to positive correlation between the performance in the self-supervised colour-differentiation task and the subsequent detection rate of actual anomalous fruits. Also, the proposed approach is evaluated on a new agricultural dataset, Riseholme-2021, consisting of 3.5K strawberry images gathered by a mobile robot, which we share online to encourage active agri-robotics research.