# Self-Supervised Features Improve Open-World Learning

arXiv: https://arxiv.org/abs/2102.07848 · HTML: https://mlsanity.com/paper/2102.07848/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 49 of its 62 references that are in the map.
- First posted on arXiv 15 Feb 2021.

## Builds on (most cited first, 30 of 49)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1603.09246/) (2016)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Colorful Image Colorization](https://mlsanity.com/paper/1603.08511/) (2016)
- [Self-Supervised Learning of Pretext-Invariant Representations](https://mlsanity.com/paper/1912.01991/) (2019)
- [Large Scale Incremental Learning](https://mlsanity.com/paper/1905.13260/) (2019)
- [Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/1902.06162/) (2019)
- [End-to-End Incremental Learning](https://mlsanity.com/paper/1807.09536/) (2018)
- [Towards Open Set Deep Networks](https://mlsanity.com/paper/1511.06233/) (2015)
- [Self-labelling via simultaneous clustering and representation learning](https://mlsanity.com/paper/1911.05371/) (2019)
- [A systematic study of the class imbalance problem in convolutional neural networks](https://mlsanity.com/paper/1710.05381/) (2017)
- [Invariant Information Clustering for Unsupervised Image Classification and Segmentation](https://mlsanity.com/paper/1807.06653/) (2018)
- [Class-incremental learning: survey and performance evaluation on image classification](https://mlsanity.com/paper/2010.15277/) (2020)
- [Do Deep Generative Models Know What They Don't Know?](https://mlsanity.com/paper/1810.09136/) (2018)
- [SCAN: Learning to Classify Images without Labels](https://mlsanity.com/paper/2005.12320/) (2020)
- [Maintaining Discrimination and Fairness in Class Incremental Learning](https://mlsanity.com/paper/1911.07053/) (2019)
- [Towards Open World Recognition](https://mlsanity.com/paper/1412.5687/) (2014)
- [Learning to Discover Novel Visual Categories via Deep Transfer Clustering](https://mlsanity.com/paper/1908.09884/) (2019)
- [Mnemonics Training: Multi-Class Incremental Learning without Forgetting](https://mlsanity.com/paper/2002.10211/) (2020)
- [Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction](https://mlsanity.com/paper/1611.09842/) (2016)
- [Scaling and Benchmarking Self-Supervised Visual Representation Learning](https://mlsanity.com/paper/1905.01235/) (2019)

## Built on by (most cited first, 8 of 8)

- [FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learning](https://mlsanity.com/paper/2211.13131/) (2022)
- [FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning](https://mlsanity.com/paper/2309.14062/) (2023)
- [Self-Supervision Can Be a Good Few-Shot Learner](https://mlsanity.com/paper/2207.09176/) (2022)
- [PlaStIL: Plastic and Stable Memory-Free Class-Incremental Learning](https://mlsanity.com/paper/2209.06606/) (2022)
- [Zero-Shot Scene Understanding for Automatic Target Recognition Using Large Vision-Language Models](https://mlsanity.com/paper/2501.07396/) (2025)
- [Human Activity Recognition in an Open World](https://mlsanity.com/paper/2212.12141/) (2022)
- [Wildlife Target Re-Identification Using Self-supervised Learning in Non-Urban Settings](https://mlsanity.com/paper/2507.02403/) (2025)
- [Complexity of Linear Regions in Self-supervised Deep ReLU Networks](https://mlsanity.com/paper/2604.24393/) (2026)

## Abstract (arXiv)

This paper identifies the flaws in existing open-world learning approaches and attempts to provide a complete picture in the form of True Open-World Learning. We accomplish this by proposing a comprehensive generalize-able open-world learning protocol capable of evaluating various components of open-world learning in an operational setting. We argue that in true open-world learning, the underlying feature representation should be learned in a self-supervised manner. Under this self-supervised feature representation, we introduce the problem of detecting unknowns as samples belonging to Out-of-Label space. We differentiate between Out-of-Label space detection and the conventional Out-of-Distribution detection depending upon whether the unknowns being detected belong to the native-world (same as feature representation) or a new-world, respectively. Our unifying open-world learning framework combines three individual research dimensions, which typically have been explored independently, i.e., Incremental Learning, Out-of-Distribution detection and Open-World Learning. Starting from a self-supervised feature space, an open-world learner has the ability to adapt and specialize its feature space to the classes in each incremental phase and hence perform better without incurring any significant overhead, as demonstrated by our experimental results. The incremental learning component of our pipeline provides the new state-of-the-art on established ImageNet-100 protocol. We also demonstrate the adaptability of our approach by showing how it can work as a plug-in with any of the self-supervised feature representation methods.