Mayank Lunayach — accepted AI-conference papers

2024

FSD: Fast Self-Supervised Single RGB-D to Categorical 3D Objects

Mayank Lunayach, Sergey Zakharov, Dian Chen, Rares Ambrus, Zsolt Kira, Muhammad Zubair Irshad

ICRA 2024poster

In this work, we address the challenging task of 3D object recognition without the reliance on real-world 3D labeled data. Our goal is to predict the 3D shape, size, and 6D pose of objects within a single RGB-D image, operating at the category level and eliminating the need for CAD models during inf…

Cited by 13 Source ↗code ↗Scholar ↗

2019

U-CAM: Visual Explanation Using Uncertainty Based Class Activation Maps

Badri N. Patro, Mayank Lunayach, Shivansh Patel, Vinay P. Namboodiri

ICCV 2019poster

Understanding and explaining deep learning models is an imperative task. Towards this, we propose a method that obtains gradient-based certainty estimates that also provide visual attention maps. Particularly, we solve for visual question answering task. We incorporate modern probabilistic deep lear…

Cited by 110 PDF ↗Scholar ↗