Publications (38)
Recognizing Scenes from Novel Viewpoints
Shengyi Qian, Alexander Kirillov, Nikhila Ravi +4
Humans can perceive scenes in 3D from a handful of 2D views. For AI agents, the ability to recognize a scene from any viewpoint given only a few images enables them to efficiently…
Semantic Curiosity for Active Visual Learning
Devendra Singh Chaplot, Helen Jiang, Saurabh Gupta +1
In this paper, we study the task of embodied interactive learning for object detection. Given a set of environments (and some labeling budget), our goal is to learn an object detec…
PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learning
Santhosh Kumar Ramakrishnan, Devendra Singh Chaplot, Ziad Al-Halah +2
State-of-the-art approaches to ObjectGoal navigation rely on reinforcement learning and typically require significant computational resources and time for learning. We propose Pote…
Global Pose Estimation with an Attention-based Recurrent Network
Emilio Parisotto, Devendra Singh Chaplot, Jian Zhang +1
The ability for an agent to localize itself within an environment is crucial for many real-world applications. For unknown environments, Simultaneous Localization and Mapping (SLAM…
FILM: Following Instructions in Language with Modular Methods
So Yeon Min, Devendra Singh Chaplot, Pradeep Ravikumar +2
Recent methods for embodied instruction following are typically trained end-to-end using imitation learning. This often requires the use of expert trajectories and low-level langua…
Differentiable Spatial Planning using Transformers
Devendra Singh Chaplot, Deepak Pathak, Jitendra Malik
We consider the problem of spatial path planning. In contrast to the classical solutions which optimize a new plan from scratch and assume access to the full map with ground truth…