Fourier Transform Approximation as an Auxiliary Task for Image Classification
This work addresses image classification enhancement for researchers, but it is incremental as it builds on existing auxiliary task conventions.
The paper tackled the problem of improving image classification performance by proposing Fourier Transform approximation as an alternative auxiliary task to image reconstruction, finding that it generally boosts accuracy on CIFAR-10 and in some cases enhances resistance to adversarial attacks.
Image reconstruction is likely the most predominant auxiliary task for image classification, but we would like to think twice about this convention. In this paper, we investigated "approximating the Fourier Transform of the input image" as a potential alternative, in the hope that it may further boost the performances on the primary task or introduce novel constraints not well covered by image reconstruction. We experimented with five popular classification architectures on the CIFAR-10 dataset, and the empirical results indicated that our proposed auxiliary task generally improves the classification accuracy. More notably, the results showed that in certain cases our proposed auxiliary task may enhance the classifiers' resistance to adversarial attacks generated using the fast gradient sign method.