Corpus ID: 53116049

Visual Semantic Navigation using Scene Priors

  title={Visual Semantic Navigation using Scene Priors},
  author={Wei Yang and X. Wang and Ali Farhadi and A. Gupta and R. Mottaghi},
  • Wei Yang, X. Wang, +2 authors R. Mottaghi
  • Published 2019
  • Computer Science
  • ArXiv
  • How do humans navigate to target objects in novel scenes. [...] Key Method The agent uses the features from the knowledge graph to predict the actions. For evaluation, we use the AI2-THOR framework. Our experiments show how semantic knowledge improves performance significantly. More importantly, we show improvement in generalization to unseen scenes and/or objects. The supplementary video can be accessed at the following link: this https URL .Expand Abstract
    79 Citations
    Utilising Prior Knowledge for Visual Navigation: Distil and Adapt
    • Highly Influenced
    Unsupervised Domain Adaptation for Visual Navigation
    • PDF
    Exploiting Scene-specific Features for Object Goal Navigation
    • PDF
    Seeing the Un-Scene: Learning Amodal Semantic Maps for Room Navigation
    • 3
    • PDF
    Target driven visual navigation exploiting object relationships
    • 2
    • Highly Influenced
    Improving Target-driven Visual Navigation with Attention on 3D Spatial Relationships
    • 1
    • PDF
    SSCNav: Confidence-Aware Semantic Scene Completion for Visual Semantic Navigation
    • PDF
    Bayesian Relational Memory for Semantic Visual Navigation
    • 24
    • Highly Influenced
    • PDF
    Neural Topological SLAM for Visual Navigation
    • 19
    • PDF
    Memory-Augmented Reinforcement Learning for Image-Goal Navigation
    • PDF


    Visual Representations for Semantic Target Driven Navigation
    • 65
    • PDF
    Target-driven visual navigation in indoor scenes using deep reinforcement learning
    • 745
    • PDF
    DeepNav: Learning to Navigate Large Cities
    • 43
    • PDF
    AI2-THOR: An Interactive 3D Environment for Visual AI
    • 233
    • PDF
    Semi-parametric Topological Memory for Navigation
    • 127
    • PDF
    Cognitive Mapping and Planning for Visual Navigation
    • 352
    Self-Supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigation
    • 136
    • PDF
    Visual Translation Embedding Network for Visual Relation Detection
    • 295
    • PDF
    Contextual Priming and Feedback for Faster R-CNN
    • 98
    • PDF
    segDeepM: Exploiting segmentation and context in deep neural networks for object detection
    • 118
    • PDF