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.
AllenAct: A Framework for Embodied AI Research
- Luca Weihs, Jordi Salvador, Aniruddha Kembhavi
- Computer ScienceArXiv
- 28 August 2020
AllenAct is introduced, a modular and flexible learning framework designed with a focus on the unique requirements of Embodied AI research that provides first-class support for a growing collection of embodied environments, tasks and algorithms.
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.
Interactron: Embodied Adaptive Object Detection
- Klemen Kotar, Roozbeh Mottaghi
- Computer ScienceComputer Vision and Pattern Recognition
- 1 February 2022
The idea is to continue training during inference and adapt the model at test time without any explicit supervision via interacting with the environment, and its performance is on par with a model trained with full supervision for those environments.
Break and Make: Interactive Structural Understanding Using LEGO Bricks
- Aaron Walsman, Muru Zhang, Klemen Kotar, Karthik Desingh, Ali Farhadi, D. Fox
- Computer ScienceEuropean Conference on Computer Vision
- 27 July 2022
This work proposes a challenging new assembly problem using LEGO bricks that an agent is given a LEGO model and attempts to understand its structure by interactively inspecting and disassembling it, using sequence-to-sequence models that provide guidance for how to make progress on this challenging problem.