Text-image Alignment for Diffusion-based Perception

1 code implementation • 29 Sep 2023 • Neehar Kondapaneni, Markus Marks, Manuel Knott, Rogerio Guimaraes, Pietro Perona

Our cross-domain segmentation method, trained on Cityscapes, achieves SOTA results on Dark Zurich-val and Nighttime Driving.

Image Generation Monocular Depth Estimation +3

Visual Knowledge Tracing

1 code implementation • 20 Jul 2022 • Neehar Kondapaneni, Pietro Perona, Oisin Mac Aodha

In this work, we propose a novel task of tracing the evolving classification behavior of human learners as they engage in challenging visual classification tasks.

Autonomous Driving General Classification +1

A Number Sense as an Emergent Property of the Manipulating Brain

1 code implementation • 8 Dec 2020 • Neehar Kondapaneni, Pietro Perona

As a result, our model acquires the ability to estimate numerosity, i. e. the number of objects in the scene, as well as subitization, i. e. the ability to recognize at a glance the exact number of objects in small scenes.