AI2-THOR: An Interactive 3D Environment for Visual AI
- Eric Kolve, Roozbeh Mottaghi, Ali Farhadi
- Computer ScienceArXiv
- 14 December 2017
AI2-THOR consists of near photo-realistic 3D indoor scenes, where AI agents can navigate in the scenes and interact with objects to perform tasks and facilitate building visually intelligent models.
Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning
- Mitchell Wortsman, Kiana Ehsani, Mohammad Rastegari, Ali Farhadi, Roozbeh Mottaghi
- Computer ScienceComputer Vision and Pattern Recognition
- 3 December 2018
A self-adaptive visual navigation method (SAVN) which learns to adapt to new environments without any explicit supervision which shows major improvements in both success rate and SPL for visual navigation in novel scenes.
Watching the World Go By: Representation Learning from Unlabeled Videos
- Daniel Gordon, Kiana Ehsani, D. Fox, Ali Farhadi
- Computer ScienceArXiv
- 18 March 2020
Video Noise Contrastive Estimation is proposed, a method for using unlabeled video to learn strong, transferable single image representations that demonstrate improvements over recent unsupervised single image techniques, as well as over fully supervised ImageNet pretraining, across a variety of temporal and non-temporal tasks.
SeGAN: Segmenting and Generating the Invisible
- Kiana Ehsani, Roozbeh Mottaghi, Ali Farhadi
- Computer ScienceIEEE/CVF Conference on Computer Vision and…
- 29 March 2017
This paper studies the challenging problem of completing the appearance of occluded objects and proposes a novel solution, SeGAN, which outperforms state-of-the-art segmentation baselines for the invisible parts of objects.
Contrasting Contrastive Self-Supervised Representation Learning Pipelines
- Klemen Kotar, Gabriel Ilharco, Ludwig Schmidt, Kiana Ehsani, Roozbeh Mottaghi
- Computer ScienceIEEE International Conference on Computer Vision
- 25 March 2021
This paper analyzes contrastive approaches as one of the most successful and popular variants of self-supervised representation learning and examines over 700 training experiments including 30 encoders, 4 pre-training datasets and 20 diverse downstream tasks.
Use the Force, Luke! Learning to Predict Physical Forces by Simulating Effects
- Kiana Ehsani, Shubham Tulsiani, Saurabh Gupta, Ali Farhadi, A. Gupta
- Computer ScienceComputer Vision and Pattern Recognition
- 26 March 2020
This paper addresses the problem of inferring contact points and the physical forces from videos of humans interacting with objects by using a physics simulator to predict effects, and enforce that estimated forces must lead to same effect as depicted in the video.
ManipulaTHOR: A Framework for Visual Object Manipulation
- Kiana Ehsani, Winson Han, Roozbeh Mottaghi
- Computer ScienceComputer Vision and Pattern Recognition
- 22 April 2021
This work proposes a framework for object manipulation built upon the physics-enabled, visually rich AI2-THOR framework and presents a new challenge to the Embodied AI community known as ArmPointNav, which extends the popular point navigation task to object manipulation and offers new challenges including 3D obstacle avoidance.
ProcTHOR: Large-Scale Embodied AI Using Procedural Generation
- Matt Deitke, Eli VanderBilt, Roozbeh Mottaghi
- Computer ScienceArXiv
- 14 June 2022
The proposed PROCTHOR, a framework for procedural generation of Embodied AI environments, enables us to sample arbitrarily large datasets of diverse, interactive, customizable, and performant virtual environments to train and evaluate embodied agents across navigation, interaction, and manipulation tasks.
Continuous Scene Representations for Embodied AI
- S. Gadre, Kiana Ehsani, Shuran Song, Roozbeh Mottaghi
- Computer ScienceComputer Vision and Pattern Recognition
- 31 March 2022
Using CSR, state-of-the-art approaches for the challenging downstream task of visual room rearrangement are outperformed, without any task specific training and the learned embeddings capture salient spatial details of the scene and show applicability to real world data.
Contrasting Contrastive Self-Supervised Representation Learning Models
- Klemen Kotar, Gabriel Ilharco, Ludwig Schmidt, Kiana Ehsani, Roozbeh Mottaghi
- Computer ScienceArXiv
- 2021
This paper analyzes contrastive approaches as one of the most successful and popular variants of self-supervised representation learning and examines over 700 training experiments including 30 encoders, 4 pre-training datasets and 20 diverse downstream tasks.
...
...