Search Results for author: Arjun Gupta

Found 17 papers, 10 papers with code

Learning Value Functions from Undirected State-only Experience

no code implementations ICLR 2022 Matthew Chang, Arjun Gupta, Saurabh Gupta

We show that LAQ can recover value functions that have high correlation with value functions learned using ground truth actions.

Future prediction Imitation Learning +3

Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks

1 code implementation NeurIPS 2021 Avi Schwarzschild, Eitan Borgnia, Arjun Gupta, Furong Huang, Uzi Vishkin, Micah Goldblum, Tom Goldstein

In this work, we show that recurrent networks trained to solve simple problems with few recurrent steps can indeed solve much more complex problems simply by performing additional recurrences during inference.

DP-InstaHide: Provably Defusing Poisoning and Backdoor Attacks with Differentially Private Data Augmentations

1 code implementation2 Mar 2021 Eitan Borgnia, Jonas Geiping, Valeriia Cherepanova, Liam Fowl, Arjun Gupta, Amin Ghiasi, Furong Huang, Micah Goldblum, Tom Goldstein

The InstaHide method has recently been proposed as an alternative to DP training that leverages supposed privacy properties of the mixup augmentation, although without rigorous guarantees.

Data Poisoning

The Uncanny Similarity of Recurrence and Depth

1 code implementation ICLR 2022 Avi Schwarzschild, Arjun Gupta, Amin Ghiasi, Micah Goldblum, Tom Goldstein

It is widely believed that deep neural networks contain layer specialization, wherein neural networks extract hierarchical features representing edges and patterns in shallow layers and complete objects in deeper layers.

Image Classification

Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphs

1 code implementation18 Jan 2021 Antoni Rosinol, Andrew Violette, Marcus Abate, Nathan Hughes, Yun Chang, Jingnan Shi, Arjun Gupta, Luca Carlone

This mental model captures geometric and semantic aspects of the scene, describes the environment at multiple levels of abstractions (e. g., objects, rooms, buildings), includes static and dynamic entities and their relations (e. g., a person is in a room at a given time).

3D Reconstruction Object Localization +2

Semantic Visual Navigation by Watching YouTube Videos

1 code implementation NeurIPS 2020 Matthew Chang, Arjun Gupta, Saurabh Gupta

Semantic cues and statistical regularities in real-world environment layouts can improve efficiency for navigation in novel environments.

Q-Learning Visual Navigation

Online Monitoring for Neural Network Based Monocular Pedestrian Pose Estimation

no code implementations11 May 2020 Arjun Gupta, Luca Carlone

We investigate the problem of online output monitoring for neural networks that estimate 3D human shapes and poses from images.

Pose Estimation Self-Driving Cars

3D Dynamic Scene Graphs: Actionable Spatial Perception with Places, Objects, and Humans

3 code implementations15 Feb 2020 Antoni Rosinol, Arjun Gupta, Marcus Abate, Jingnan Shi, Luca Carlone

Our second contribution is to provide the first fully automatic Spatial PerceptIon eNgine(SPIN) to build a DSG from visual-inertial data.

3D Reconstruction Human Detection +3

Cannot find the paper you are looking for? You can Submit a new open access paper.