1 code implementation • 24 Mar 2024 • Siddharth Tourani, Ahmed Alwheibi, Arif Mahmood, Muhammad Haris Khan
Second, motivated by the ZeroShot performance, we develop a ULD algorithm based on diffusion features using self-training and clustering which also outperforms prior methods by notable margins.
no code implementations • 18 Jul 2023 • Siddharth Tourani, Carsten Rother, Muhammad Haris Khan, Bogdan Savchynskyy
We contribute to the sparsely populated area of unsupervised deep graph matching with application to keypoint matching in images.
1 code implementation • 16 Apr 2020 • Siddharth Tourani, Alexander Shekhovtsov, Carsten Rother, Bogdan Savchynskyy
We consider the maximum-a-posteriori inference problem in discrete graphical models and study solvers based on the dual block-coordinate ascent rule.
no code implementations • ECCV 2018 • Siddharth Tourani, Alexander Shekhovtsov, Carsten Rother, Bogdan Savchynskyy
Dense, discrete Graphical Models with pairwise potentials are a powerful class of models which are employed in state-of-the-art computer vision and bio-imaging applications.