Robustness

Robust Learning Through Cross-Task Consistency

Visual perception entails solving a wide set of tasks, e.g., object detection, depth estimation, etc. The predictions made for multiple tasks from the same image are not independent, and therefore, are expected to be 'consistent'. We propose a …

Mid-Level Visual Priors Improve Generalization and Sample Efficiency for Learning Visuomotor Policies

How much does having **visual priors about the world** (e.g. the fact that the world is 3D) assist in learning to perform **downstream motor tasks** (e.g. delivering a package)? We study this question by integrating a generic perceptual skill set …

GibsonEnv: Embodied Real-World Active Perception

Perception and being active (i.e. having a certain level of motion freedom) are closely tied. Learning active perception and sensorimotor control in the physical world is cumbersome as existing algorithms are too slow to efficiently learn in …

2D-3D-Semantic Data for Indoor Scene Understanding

We present a dataset of large-scale indoor spaces that provides a variety of mutually registered modalities from 2D, 2.5D and 3D domains, with instance-level semantic and geometric annotations. The dataset covers over 6,000 m2 and contains over …