# Feature Decoupling in Self-supervised Representation Learning for Open Set Recognition

arXiv: https://arxiv.org/abs/2209.14385 · HTML: https://mlsanity.com/paper/2209.14385/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 32 references that are in the map.
- First posted on arXiv 28 Sep 2022.

## Builds on (most cited first, 23 of 23)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Graph Contrastive Learning with Augmentations](https://mlsanity.com/paper/2010.13902/) (2020)
- [Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery](https://mlsanity.com/paper/1703.05921/) (2017)
- [Towards Open Set Deep Networks](https://mlsanity.com/paper/1511.06233/) (2015)
- [Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples](https://mlsanity.com/paper/1711.09325/) (2017)
- [Reducing Network Agnostophobia](https://mlsanity.com/paper/1811.04110/) (2018)
- [Generative OpenMax for Multi-Class Open Set Classification](https://mlsanity.com/paper/1707.07418/) (2017)
- [Classification-Reconstruction Learning for Open-Set Recognition](https://mlsanity.com/paper/1812.04246/) (2018)
- [Learning Placeholders for Open-Set Recognition](https://mlsanity.com/paper/2103.15086/) (2021)
- [Revisiting Training Strategies and Generalization Performance in Deep Metric Learning](https://mlsanity.com/paper/2002.08473/) (2020)
- [Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learning](https://mlsanity.com/paper/2105.05682/) (2021)
- [Microsoft Malware Classification Challenge](https://mlsanity.com/paper/1802.10135/) (2018)
- [Learning a Neural-network-based Representation for Open Set Recognition](https://mlsanity.com/paper/1802.04365/) (2018)
- [Open-Category Classification by Adversarial Sample Generation](https://mlsanity.com/paper/1705.08722/) (2017)
- [Reconstruction-Based Disentanglement for Pose-invariant Face Recognition](https://mlsanity.com/paper/1702.03041/) (2017)
- [ODN: Opening the Deep Network for Open-set Action Recognition](https://mlsanity.com/paper/1901.07757/) (2019)
- [MMF: A loss extension for feature learning in open set recognition](https://mlsanity.com/paper/2006.15117/) (2020)
- [Self-supervised Detransformation Autoencoder for Representation Learning in Open Set Recognition](https://mlsanity.com/paper/2105.13557/) (2021)
- [Representation learning with function call graph transformations for malware open set recognition](https://mlsanity.com/paper/2205.06918/) (2022)

## Abstract (arXiv)

Assuming unknown classes could be present during classification, the open set recognition (OSR) task aims to classify an instance into a known class or reject it as unknown. In this paper, we use a two-stage training strategy for the OSR problems. In the first stage, we introduce a self-supervised feature decoupling method that finds the content features of the input samples from the known classes. Specifically, our feature decoupling approach learns a representation that can be split into content features and transformation features. In the second stage, we fine-tune the content features with the class labels. The fine-tuned content features are then used for the OSR problems. Moreover, we consider an unsupervised OSR scenario, where we cluster the content features learned from the first stage. To measure representation quality, we introduce intra-inter ratio (IIR). Our experimental results indicate that our proposed self-supervised approach outperforms others in image and malware OSR problems. Also, our analyses indicate that IIR is correlated with OSR performance.