Deep CNN-based Multi-task Learning for Open-Set Recognition

Abstract

We propose a novel deep convolutional neural network (CNN) based multi-task learning approach for open-set visual recognition. We combine a classifier network and a decoder network with a shared feature extractor network within a multi-task learning framework. We show that this approach results in better open-set recognition accuracy. In our approach, reconstruction errors from the decoder network are utilized for open-set rejection. In addition, we model the tail of the reconstruction error distribution from the known classes using the statistical Extreme Value Theory to improve the overall performance. Experiments on multiple image classification datasets are performed and it is shown that this method can perform significantly better than many competitive open set recognition algorithms available in the literature. The code will be made available at: github.com/otkupjnoz/mlosr.

Under Review

References in corpus (6)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• Deep Anomaly Detection with Outlier Exposure
• The Extreme Value Machine
• Open Category Detection with PAC Guarantees

Cited by in corpus (8)

• Visual Identification of Individual Holstein-Friesian Cattle via Deep Metric Learning
• Collective Decision of One-vs-Rest Networks for Open Set Recognition
• A Survey on Open Set Recognition
• Adversarial Motorial Prototype Framework for Open Set Recognition
• Domain segmentation and adjustment for generalized zero-shot learning
• Teacher-Explorer-Student Learning: A Novel Learning Method for Open Set Recognition
• Attention-Aware Age-Agnostic Visual Place Recognition
• Open-set Recognition based on the Combination of Deep Learning and Ensemble Method for Detecting Unknown Traffic Scenarios