Data Attribution on Progressive Datasets for Deep Learning

Deep convolutional networks are able to learn representation of images, scoring well in tasks such as image classification and object detection. During model training, these networks have the ability to process different input sizes without requiring changes to their architecture. In this project, we would like to investigate the effects that changing input sizes has on these kinds of models. We want to do this by investigating and using data attribution methods, as these techniques can help explain the effect of input data on the predictions of the model. The result is a better understanding of the effects of scaled input on convolutional models, as well as a better understanding of the hardware and resource benefits scaling techniques can offer to model training. If your interests lie at the intersection of machine learning and systems performance, this project would be a great fit for you.

This project would be suitable as a standalone project or BSc or MSc thesis at ITU during Fall 2024. Based on the size of the project and the interests of the student(s), we can target all or a subset of the tasks above.