DeepAI AI Chat
Log In Sign Up

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

by   Jingyun Jia, et al.
Florida Institute of Technology

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.


page 3

page 8


Representation learning with function call graph transformations for malware open set recognition

Open set recognition (OSR) problem has been a challenge in many machine ...

Self-supervised Detransformation Autoencoder for Representation Learning in Open Set Recognition

The objective of Open set recognition (OSR) is to learn a classifier tha...

Learning To Classify Images Without Labels

Is it possible to automatically classify images without the use of groun...

Out-of-Distribution Detection without Class Labels

Anomaly detection methods identify samples that deviate from the normal ...

Training set cleansing of backdoor poisoning by self-supervised representation learning

A backdoor or Trojan attack is an important type of data poisoning attac...

Learning a Neural-network-based Representation for Open Set Recognition

Open set recognition problems exist in many domains. For example in secu...

Self-Supervised Features Improve Open-World Learning

This is a position paper that addresses the problem of Open-World learni...