Artur Jesslen
@arturjssl.bsky.social
🇫🇷🇨🇭| PhD student @ Uni Freiburg 🇩🇪 | Generative Vision | 3D understanding | #QueerInAI 🏳️🌈
Reposted by Artur Jesslen
In “Scaling 3D Compositional Models for Robust Classification and Pose Estimation,” @jhu.edu researchers & @arturjssl.bsky.social + @adamkortylewski.bsky.social exploit the compositionality of objects to reduce DL algorithm training time ⌚️ & improve performance: openreview.net/forum?id=waG... (8/10)
Scaling 3D Compositional Models for Robust Classification and Pose...
Deep learning algorithms for object classification and 3D object pose estimation lack robustness to out-of-distribution factors such as synthetic stimuli, changes in weather conditions, and partial...
openreview.net
October 16, 2025 at 8:18 PM
In “Scaling 3D Compositional Models for Robust Classification and Pose Estimation,” @jhu.edu researchers & @arturjssl.bsky.social + @adamkortylewski.bsky.social exploit the compositionality of objects to reduce DL algorithm training time ⌚️ & improve performance: openreview.net/forum?id=waG... (8/10)