Timezone: »

 
Inductive Biases for Object-Centric Representations in the Presence of Complex Textures
Samuele Papa · Ole Winther · Andrea Dittadi

Fri Jul 22 12:15 PM -- 01:15 PM (PDT) @
in Dynamic Neural Networks »

Understanding which inductive biases could be helpful for the unsupervised learning of object-centric representations of natural scenes is challenging. In this paper, we use neural style transfer to generate datasets where objects have complex textures while still retaining ground-truth annotations. We find that methods that use a single module to reconstruct both the shape and visual appearance of each object learn more useful representations and achieve better object separation. In addition, we observe that adjusting the latent space size is insufficient to improve segmentation performance. Finally, the downstream usefulness of the representations is significantly more strongly correlated with segmentation quality than with reconstruction accuracy.

[ Poster] 

Author Information

Samuele Papa (University of Amsterdam)
Samuele Papa

I have a background in information engineering, computer engineering, and artificial intelligence. In 2021 I completed both an MSc (cum laude) in Computer Engineering at the University of Padova and an MSc in Human-Centered Artificial Intelligence at the Technical University of Denmark. During my studies, I focused on fundamental research in the field of Deep Learning, specifically on how to obtain useful representations of images to enable the automation of higher-level cognitive tasks. I am now a PhD candidate under the POP-AART Lab (2021-2024), a collaboration between Elekta, the University of Amsterdam, and the Netherlands Cancer Institute. The aim of the collaboration is personalized online radiotherapy using artificial intelligence methods. The lab is supervised by Jan-Jakob Sonke and Efstratios Gavves. I will focus on using deep generative models to improve the quality of Cone Beam Computed Tomography (CBCT) while enforcing geometric and pathological integrity.

Ole Winther (DTU and KU)
Andrea Dittadi (Technical University of Denmark)

More from the Same Authors