Achal Dave

Hi! I'm a Research Scientist at Toyota Research Institute. Previously, I was an Applied Scientist at Amazon, before which I was 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

[2022.09.25]: Check out our new BURST benchmark: TAO with segmentation masks!
[2022.07.08]: Detecting Invisible People was covered by NBC Universal
[2022.07.03]: Our paper "Differentiable Raycasting for Self-supervised Occupancy Forecasting" was accepted to ECCV 2022.
[2022.05.15]: Our paper (Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP) was accepted to ICML 2022.
[2022.03.01]: Our paper (Opening up Open-World Tracking) was accepted as an oral to CVPR 2022.
[2021.07.29]: Two papers (Do Image Classifiers Generalize Across Time? and Detecting Invisible People) were accepted to ICCV '21!
[2021.07.28]: Check out Open CLIP, our open-source implementation of OpenAI's CLIP.

Research

BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video

Ali Athar, Jonathon Luiten, Paul Voigtlander, Tarasha Khurana, Achal Dave, Bastian Leibe, Deva Ramanan

In submission

Differentiable Raycasting for Self-supervised Occupancy Forecasting

Tarasha Khurana*, Peiyun Hu*, Achal Dave, Jason Ziglar, David Held, Deva Ramanan

ECCV 2022

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]

Yang Liu*, Idil Esen Zulfikar*, Jonathon Luiten*, Achal Dave*, Deva Ramanan, Bastian Leibe, Aljoša Ošep, Laura Leal-Taixé

CVPR 2022, Oral

Evaluating Large-Vocabulary Object Detectors: The Devil is in the Details [ArXiV]

Achal Dave, Piotr Dollár, Deva Ramanan, Alexander Kirillov, Ross Girshick

ArXiV

Detecting Invisible People [paper]

Tarasha Khurana, Achal Dave, Deva Ramanan

ICCV 2021

TAO: A Large-Scale Benchmark for Tracking Any Object [paper, website, code]

Achal Dave, Tarasha Khurana, Pavel Tokmakov, Cordelia Schmid, Deva Ramanan

ECCV 2020 (Spotlight)

Measuring Robustness to Natural Distribution Shifts in Image Classification [paper, website, code, interactive plots]

Rohan Taori, Achal Dave, Vaishaal Shankar, Nicholas Carlini, Ben Recht, Ludwig Schmidt

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

Learning to Track Any Object [paper]

Achal Dave*, Pavel Tokmakov, Cordelia Schmid, Deva Ramanan

ICCV Workshop on Holistic Video Understanding, 2019

Towards Segmenting Anything That Moves [paper, website]

Achal Dave, Pavel Tokmakov, Deva Ramanan

ICCV Workshop on Holistic Video Understanding, 2019

Predictive-Corrective Networks for Action Detection [paper, bibtex, website]

Achal Dave, Olga Russakovsky, Deva Ramanan

CVPR 2017

HOBS: Head Orientation-Based Selection in Physical Spaces [paper, slides, doi, code]

Ben Zhang, Yu-Hsiang Chen, Claire Tuna, Achal Dave, Yang Li, Edward A. Lee and Björn Hartmann

ACM Symposium on Spatial User Interaction (SUI2014)

Projects

PyTorch Feature Extraction: Extract features from a number of pretrained deep networks.
Action detection visualizer: Visualize videos, groundtruth annotations, and predictions.
Video tools: Useful utilities for working with videos
Tutorial links: A collection of useful tutorials from the web on various machine learning topics.

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