mlsanityData to 14 Oct 2026

Unbiased Directed Object Attention Graph for Object Navigation

arXiv 2204.04421 ↗First posted 9 Apr 2022cs.CV cs.AIcited by 18

Not on the map. Why?

Abstract (arXiv)

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%, 8.1% and 17.6% increase in success rate (SR), success weighted by path length (SPL) and success weighted by action efficiency (SAE), respectively.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). Builds on 30 of its 46 references that are in the map. First posted on arXiv 9 Apr 2022.

Builds on

30 of 46 references.

References · 30

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  6. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  7. 2017Non-local Neural Networkscited by 2,293
  8. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
  9. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  10. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
  11. 2019Habitat: A Platform for Embodied AI Researchcited by 1,191
  12. 2017AI2-THOR: An Interactive 3D Environment for Visual AIcited by 869
18 more
  1. 2018On Evaluation of Embodied Navigation Agentscited by 547
  2. 2020Object Goal Navigation using Goal-Oriented Semantic Explorationcited by 429
  3. 2020Unbiased Scene Graph Generation from Biased Trainingcited by 356
  4. 2019REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environmentscited by 333
  5. 2016Learning to Navigate in Complex Environmentscited by 198
  6. 2020RoboTHOR: An Open Simulation-to-Real Embodied AI Platformcited by 193
  7. 2019RUBi: Reducing Unimodal Biases in Visual Question Answeringcited by 185
  8. 2019REPAIR: Removing Representation Bias by Dataset Resamplingcited by 157
  9. 2021Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generationcited by 137
  10. 2018Visual Semantic Navigation using Scene Priorscited by 128
  11. 2021SOON: Scenario Oriented Object Navigation with Graph-based Explorationcited by 119
  12. 2018Building Generalizable Agents with a Realistic and Rich 3D Environmentcited by 109
  13. 2018Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learningcited by 93
  14. 2021Auxiliary Tasks and Exploration Enable ObjectNavcited by 74
  15. 2015Seeing through the Human Reporting Bias: Visual Classifiers from Noisy Human-Centric Labelscited by 64
  16. 2020Learning Object Relation Graph and Tentative Policy for Visual Navigationcited by 64
  17. 2021SOAT: A Scene- and Object-Aware Transformer for Vision-and-Language Navigationcited by 53
  18. 2021Hierarchical Object-to-Zone Graph for Object Navigationcited by 34

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 6; 2024: 6; 2025: 2; 2026: 3.

18 papers.

Sort:

By area:

  1. 2024Vision-and-Language Navigation via Causal Learningcited by 51
  2. 2022Search for or Navigate to? Dual Adaptive Thinking for Object Navigationcited by 20
  3. 2023A Dual Semantic-Aware Recurrent Global-Adaptive Network For Vision-and-Language Navigationcited by 18
  4. 2023Graph based Environment Representation for Vision-and-Language Navigation in Continuous Environmentscited by 9
  5. 2023Multiple Thinking Achieving Meta-Ability Decoupling for Object Navigationcited by 8
  6. 2023PASTS: Progress-Aware Spatio-Temporal Transformer Speaker For Vision-and-Language Navigationcited by 8
  7. 2024MAGIC: Meta-Ability Guided Interactive Chain-of-Distillation for Effective-and-Efficient Vision-and-Language Navigationcited by 6
  8. 2023Implicit Obstacle Map-driven Indoor Navigation Model for Robust Obstacle Avoidancecited by 3
  9. 2023Building Category Graphs Representation with Spatial and Temporal Attention for Visual Navigationcited by 2
  10. 2025SEA: Semantic Map Prediction for Active Exploration of Uncertain Areascited by 2
  11. 2026A Comprehensive Survey and Systematic Real-World Evaluation of Embodied Vision-and-Language Navigationcited by 1
  12. 2024Causality-based Cross-Modal Representation Learning for Vision-and-Language Navigationcited by 0
6 more
  1. 2024Temporal-Spatial Object Relations Modeling for Vision-and-Language Navigationcited by 0
  2. 2024Leveraging Unknown Objects to Construct Labeled-Unlabeled Meta-Relationships for Zero-Shot Object Navigationcited by 0
  3. 2024Efficient Strategy Learning by Decoupling Searching and Pathfinding for Object Navigationcited by 0
  4. 2025Recursive Visual Imagination and Adaptive Linguistic Grounding for Vision Language Navigationcited by 0
  5. 2026Enhancing Vision-Language Navigation with Multimodal Event Knowledge from Real-World Indoor Tour Videoscited by 0
  6. 2026Graph-MambaNav: Spatial-Temporal Graph Mamba Leveraging Object-Relation Knowledge for Object-Goal Navigationcited by 0