Mahsa Baktashmotlagh

A new framework enhances 3D object detection by addressing domain adaptation challenges.

Exploring effective ways to choose dense retrieval models for unlabeled data.

A method to improve dense retriever selection using LLMs without requiring labels.

A new method enhances 3D object detection systems for varied environments.

DiPEx improves object detection rates using unique, diverse prompts.

Introducing a method to estimate model performance without relying on training data.

AutoPalette reduces color clutter in datasets for more efficient machine learning.

Investigating how viewpoint changes affect object recognition in vision models.