Deep CNN-based Multi-task Learning for Open-Set Recognition
This work addresses the problem of open-set recognition in computer vision, which is important for real-world applications where unknown classes may appear, but it is incremental as it builds on existing multi-task and reconstruction-based techniques.
The paper tackles open-set visual recognition by proposing a deep CNN-based multi-task learning approach that combines a classifier and decoder with a shared feature extractor, using reconstruction errors and Extreme Value Theory for rejection, resulting in significantly better accuracy than competitive methods on multiple image datasets.
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.