Blindfold Baselines for Embodied QA

Abstract

We explore blindfold (question-only) baselines for Embodied Question Answering. The EmbodiedQA task requires an agent to answer a question by intelligently navigating in a simulated environment, gathering necessary visual information only through first-person vision before finally answering. Consequently, a blindfold baseline which ignores the environment and visual information is a degenerate solution, yet we show through our experiments on the EQAv1 dataset that a simple question-only baseline achieves state-of-the-art results on the EmbodiedQA task in all cases except when the agent is spawned extremely close to the object.

NIPS 2018 Visually-Grounded Interaction and Language (ViGilL) Workshop

References in corpus (3)

• AI2-THOR: An Interactive 3D Environment for Visual AI
• Building Generalizable Agents with a Realistic and Rich 3D Environment
• Exploring Nearest Neighbor Approaches for Image Captioning

Cited by in corpus (15)

• RUBi: Reducing Unimodal Biases in Visual Question Answering
• Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases
• Graph Density-Aware Losses for Novel Compositions in Scene Graph Generation
• Visual Dialogue without Vision or Dialogue
• Embodied Question Answering in Photorealistic Environments with Point Cloud Perception
• Deep Learning for Embodied Vision Navigation: A Survey
• Are You Looking? Grounding to Multiple Modalities in Vision-and-Language Navigation
• Interactive Language Learning by Question Answering
• VideoNavQA: Bridging the Gap between Visual and Embodied Question Answering
• Multi-Target Embodied Question Answering
• Bayesian Relational Memory for Semantic Visual Navigation
• Misleading Failures of Partial-input Baselines
• Challenges and Prospects in Vision and Language Research
• A Revised Generative Evaluation of Visual Dialogue
• Why can't memory networks read effectively?