DeepAI AI Chat
Log In Sign Up

Unbiased Directed Object Attention Graph for Object Navigation

04/09/2022
by   Ronghao Dang, et al.
Tongji University
Microsoft
ETH Zurich
0

Object navigation tasks require agents to locate specific objects in unknown environments based on visual information. Previously, graph convolutions were used to implicitly explore the relationships between objects. However, due to differences in visibility among objects, it is easy to generate biases in object attention. Thus, in this paper, we propose a directed object attention (DOA) graph to guide the agent in explicitly learning the attention relationships between objects, thereby reducing the object attention bias. In particular, we use the DOA graph to perform unbiased adaptive object attention (UAOA) on the object features and unbiased adaptive image attention (UAIA) on the raw images, respectively. To distinguish features in different branches, a concise adaptive branch energy distribution (ABED) method is proposed. We assess our methods on the AI2-Thor dataset. Compared with the state-of-the-art (SOTA) method, our method reports 7.4 (SR), success weighted by path length (SPL) and success weighted by action efficiency (SAE), respectively.

READ FULL TEXT

page 2

page 5

page 8

page 13

08/01/2022

Search for or Navigate to? Dual Adaptive Thinking for Object Navigation

"Search for" or "Navigate to"? When finding an object, the two choices a...
04/20/2021

Visual Navigation with Spatial Attention

This work focuses on object goal visual navigation, aiming at finding th...
11/29/2021

Agent-Centric Relation Graph for Object Visual Navigation

Object visual navigation aims to steer an agent towards a target object ...
09/05/2021

Hierarchical Object-to-Zone Graph for Object Navigation

The goal of object navigation is to reach the expected objects according...
05/19/2021

VSGM – Enhance robot task understanding ability through visual semantic graph

In recent years, developing AI for robotics has raised much attention. T...
05/21/2020

MBA-RainGAN: Multi-branch Attention Generative Adversarial Network for Mixture of Rain Removal from Single Images

Rain severely hampers the visibility of scene objects when images are ca...