Fashion and Apparel Classification using Convolutional Neural Networks
This work addresses metadata enrichment for e-commerce applications, but it is incremental as it applies existing CNN methods to fashion data without introducing new techniques.
The authors tackled fashion and apparel image classification to enhance e-commerce metadata by evaluating five CNN architectures on tasks like person detection and gender classification across two datasets, achieving results that improved classification accuracy but without specific numerical gains reported.
We present an empirical study of applying deep Convolutional Neural Networks (CNN) to the task of fashion and apparel image classification to improve meta-data enrichment of e-commerce applications. Five different CNN architectures were analyzed using clean and pre-trained models. The models were evaluated in three different tasks person detection, product and gender classification, on two small and large scale datasets.