Data Fine-tuning
This addresses the challenge of adapting inaccessible commercial models for specific applications, though it is incremental as it builds on adversarial perturbation techniques.
The paper tackles the problem of fine-tuning black-box commercial facial analysis systems by proposing Data Fine-tuning, which adds imperceptible noise to input images to improve classification accuracy without modifying model parameters, achieving effective results on LFW, CelebA, and MUCT datasets.
In real-world applications, commercial off-the-shelf systems are utilized for performing automated facial analysis including face recognition, emotion recognition, and attribute prediction. However, a majority of these commercial systems act as black boxes due to the inaccessibility of the model parameters which makes it challenging to fine-tune the models for specific applications. Stimulated by the advances in adversarial perturbations, this research proposes the concept of Data Fine-tuning to improve the classification accuracy of a given model without changing the parameters of the model. This is accomplished by modeling it as data (image) perturbation problem. A small amount of "noise" is added to the input with the objective of minimizing the classification loss without affecting the (visual) appearance. Experiments performed on three publicly available datasets LFW, CelebA, and MUCT, demonstrate the effectiveness of the proposed concept.