← Search

Dishank Bansal

2 accepted papers

2023

TaskMet: Task-driven Metric Learning for Model Learning

NeurIPS 2023poster

Deep learning models are often used with some downstream task. Models solely trained to achieve accurate predictions may struggle to perform well on the desired downstream tasks. We propose using the task loss to learn a metric which parameterizes a loss to train the model. This approach does not al…

2022

f-Cal: Aleatoric uncertainty quantification for robot perception via calibrated neural regression

ICRA 2022poster

While modern deep neural networks are performant perception modules, performance (accuracy) alone is insufficient, particularly for safety-critical robotic applications such as self-driving vehicles. Robot autonomy stacks also require these otherwise blackbox models to produce reliable and calibrate…

Cited by 2SourceScholar