Work

DiMViDA: Diffusion-Based Multi-View Data Augmentation

Year: 2024

Type: conference-paper

Abstract: We present DiMViDA, a Diffusion-based Multi-View Data Augmentation method built upon an innovative approach for Novel View Synthesis, which uses an extension of diffusion generative models that accepts any number of input views and that can generate any number of missing output views. In this work, our goal is to analyze the benefits of such a generative model in the context of object classification. Given a single input view, we compare the object classification performance of state-of-the-art models, namely ResNet18 and MobileNetV3, using the input view, versus its application to novel views synthesized by our generative model, using such synthetic views to augment the training set. Notably, differently from other works, we also adopt such a multi-view data augmentation method at inference. Our experimental findings illustrate that novel view synthesis can enhance object classification capabilities.

Source: IEEE International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD)

DOI: 10.1109/camad62243.2024.10942815

Authors: G. Di Giacomo, G. Franzese, T. Cerquitelli, C. F. Chiasserini, P. Michiardi

Institutions: Politecnico di Torino, EURECOM

Language: English

Topic: Generative Adversarial Networks and Image Synthesis

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: European Commission

Award: Distributed Artificial Intelligence-driven open and programmable architecture for 6G networks