Achal Dave
Hi! I'm a Research Scientist at Toyota Research Institute. I build generative models for text and videos, with a focus on improving training efficiency and dataset quality. Previously, I was an Applied Scientist at Amazon, and a Ph.D. student at Carnegie Mellon University advised by Prof. Deva Ramanan, working on open-world object detection and tracking.
Email: achal.dave@tri.global, achalddave@gmail.com

News

Projects

Recent and selected work

pix2gestalt: Amodal Segmentation by Synthesizing Wholes
In submission
Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP) [ArXiV]
Alex Fang, Gabriel Ilharco, Mitchell Wortsman, Yuhao Wan, Vaishaal Shankar, Achal Dave, Ludwig Schmidt
ICML 2022
Opening up Open-World Tracking [ArXiV]
CVPR 2022, Oral
Evaluating Large-Vocabulary Object Detectors: The Devil is in the Details [ArXiV]
ArXiV
Detecting Invisible People [paper]
ICCV 2021
TAO: A Large-Scale Benchmark for Tracking Any Object [paper, website, code]
ECCV 2020 (Spotlight)
Measuring Robustness to Natural Distribution Shifts in Image Classification [paper, website, code]
NeurIPS, 2020. Spotlight.
Do Image Classifiers Generalize Across Time? [paper, website]
Vaishaal Shankar*, Achal Dave*, Rebecca Roelofs, Deva Ramanan, Ben Recht, Ludwig Schmidt
* Equal contribution
ICCV, 2021
Most of my projects can be found on my Github.

Fun Stuff

PSYCHO: PerSonalitY CHaracterizatiOn of artificial intelligence [paper]
Achal Dave, Rohit Girdhar
SIGBOVIK 2018