Bashirul Azam Biswas

2 accepted papers

2024

Optimization-based Uncertainty Attribution Via Learning Informative Perturbations

Hanjing Wang*, Bashirul Azam Biswas, Qiang Ji

ECCV 2024poster

"Uncertainty attribution (UA) aims to identify key contributors to predictive uncertainty in deep learning models. To improve the faithfulness of existing UA methods, we formulate UA as an optimization problem to learn a binary mask on the input. The learned mask identifies regions that significantl…

Cited by 2 Source ↗PDF ↗Scholar ↗

2023

Probabilistic Debiasing of Scene Graphs

Bashirul Azam Biswas, Qiang Ji

CVPR 2023poster

The quality of scene graphs generated by the state-of-the-art (SOTA) models is compromised due to the long-tail nature of the relationships and their parent object pairs. Training of the scene graphs is dominated by the majority relationships of the majority pairs and, therefore, the object-conditio…

Cited by 26 Source ↗PDF ↗code ↗Scholar ↗