I am currently doing an internship at Samsung Research UK under the supervision of Umberto Michieli and Mete Ozay.

I am a third year Ph.D. student in Information Engineering at the University of Padova (Italy), under the supervision of Prof. Pietro Zanuttigh. On December 2nd, 2024, I submitted the final version of my Ph.D. thesis.

From May to November 2023, I was a research intern at Mila - Quebec AI Institute & Concordia University, under the supervision of Prof. Eugene Belilovsky.

During my Ph.D. I worked on large-scale machine learning problems and their application to visual understanding, in particular I worked on Federated Learning, Continual Learning, Domain Adaptation, and Semantic Segmentation. Recently, I’m working on Model Merging and Image Generation.

[Download CV]

Publications

Preprints

ABS

[P1] D. Shenaj, O. Bohdal, M. Ozay, P. Zanuttigh, U. Michieli, "LoRA.rar: Learning to Merge LoRAs via Hypernetworks for Subject-Style Conditioned Image Generation", arXiv:2412.05148, 2024. [paper][code][video]

Conferences

ABS

[C4] G. Rizzoli*, M. Caligiuri*, D. Shenaj, F. Barbato, P. Zanuttigh, "When Cars meet Drones: Hyperbolic Federated Learning for Source-Free Domain Adaptation in Adverse Weather", IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025. [paper][code]

ABS

[C3] G. Rizzoli, D. Shenaj, P Zanuttigh, "Source-Free Domain Adaptation for RGB-D Semantic Segmentation with Vision Transformers", IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Pretrain Workshop 2024. [paper]
ABS

[C2] D. Shenaj, M. Toldo, A. Rigon, P. Zanuttigh, "Asynchronous Federated Continual Learning", IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), FedVision Workshop, 2023. [paper][code]
ABS

[C1] D. Shenaj*, E. Fanì*, M. Toldo, D. Caldarola, A. Tavera, U. Michieli†, M. Ciccone†, P. Zanuttigh†, B. Caputo†, “Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning”, IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023. [paper][code]

Journals

ABS

[J2] D. Shenaj*, G. Rizzoli*, P. Zanuttigh, "Federated Learning in Computer Vision", IEEE Access, 2023. [paper]

ABS

[J1] D. Shenaj, F. Barbato, U. Michieli, P. Zanuttigh, "Continual coarse-to-fine domain adaptation in semantic segmentation", Elsevier Image and Vision Computing, 2022. [paper][webpage][code]

* Equal contribution. † Equal supervision.

Ph.D., Master’s and Bachelor’s Thesis

[T3] D. Shenaj, “Morphing Distributed and Transfer Learning Paradigms for Visual Understanding”, Ph.D thesis in Information Engineering, University of Padova, (Submitted) December 2024.

[T2] D. Shenaj, “Coarse-to-Fine Learning for Semantic Segmentaion across Multiple Domains”, MS thesis in ICT for Internet and Multimedia, University of Padova, September 2021.

[T1] D. Shenaj, “Implementation and analysis of a vehicle counter system with Python and OpenCV”, BS thesis in Electronics Engineering for Energy and Information, University of Bologna, October 2019.