Image classiffication (multi-label) on VOC2012 Dataset.
In this work, a series of deep learning models have been developed for image classification using the Pascal Visual Object Challenge 2012 (VOC2012). This dataset contains images representing one or more objects, including people, animals, vehicles, and household items.
The adopted approach consists of training a CNN from scratch, exploring the self-supervised learning paradigm, and adapting pre-trained deep neural models such as ResNet50, VGG16, and MobileNet.
Give a look to the relation for more details (currently only in italian).