• Computer Science
  • Published in ICLR 2018

Visual Semantic Navigation using Scene Priors

@article{Yang2018VisualSN,
  title={Visual Semantic Navigation using Scene Priors},
  author={Wei Yang and Xiaolong Wang and Ali Farhadi and Abhinav Gupta and Roozbeh Mottaghi},
  journal={ArXiv},
  year={2018},
  volume={abs/1810.06543}
}
How do humans navigate to target objects in novel scenes? Do we use the semantic/functional priors we have built over years to efficiently search and navigate? For example, to search for mugs, we search cabinets near the coffee machine and for fruits we try the fridge. In this work, we focus on incorporating semantic priors in the task of semantic navigation. We propose to use Graph Convolutional Networks for incorporating the prior knowledge into a deep reinforcement learning framework. The… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 23 CITATIONS

Visual Object Search by Learning Spatial Context

VIEW 20 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Generalization to Novel Objects using Prior Relational Knowledge

VIEW 6 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

Reinforcement Learning Based Navigation with Semantic Knowledge of Indoor Environments

VIEW 6 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Bayesian Relational Memory for Semantic Visual Navigation

VIEW 3 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Reinforcement Learning based Visual Navigation with Information-Theoretic Regularization

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

A Behavioral Approach to Visual Navigation with Graph Localization Networks

VIEW 2 EXCERPTS
CITES METHODS & BACKGROUND

Context-Aware Zero-Shot Recognition

VIEW 3 EXCERPTS
CITES METHODS

HiCoRe: Visual Hierarchical Context-Reasoning

VIEW 2 EXCERPTS
CITES RESULTS & BACKGROUND

References

Publications referenced by this paper.
SHOWING 1-10 OF 54 REFERENCES

Asynchronous Methods for Deep Reinforcement Learning

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Semi-Supervised Classification with Graph Convolutional Networks

VIEW 14 EXCERPTS
HIGHLY INFLUENTIAL

Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Deep Residual Learning for Image Recognition

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Target-driven visual navigation in indoor scenes using deep reinforcement learning

VIEW 3 EXCERPTS

Visual Representations for Semantic Target Driven Navigation

VIEW 1 EXCERPT