mlsanityData to 14 Oct 2026

Evaluating Explanation Methods for Vision-and-Language Navigation

arXiv 2310.06654 ↗First posted 10 Oct 2023cs.RO cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

The ability to navigate robots with natural language instructions in an unknown environment is a crucial step for achieving embodied artificial intelligence (AI). With the improving performance of deep neural models proposed in the field of vision-and-language navigation (VLN), it is equally interesting to know what information the models utilize for their decision-making in the navigation tasks. To understand the inner workings of deep neural models, various explanation methods have been developed for promoting explainable AI (XAI). But they are mostly applied to deep neural models for image or text classification tasks and little work has been done in explaining deep neural models for VLN tasks. In this paper, we address these problems by building quantitative benchmarks to evaluate explanation methods for VLN models in terms of faithfulness. We propose a new erasure-based evaluation pipeline to measure the step-wise textual explanation in the sequential decision-making setting. We evaluate several explanation methods for two representative VLN models on two popular VLN datasets and reveal valuable findings through our experiments.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 32 of its 36 references that are in the map. First posted on arXiv 10 Oct 2023.

Builds on

32 of 36 references.

References · 32

  1. 2017Attention Is All You Needcited by 60,361
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  3. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  4. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  5. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  6. 2017Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentscited by 1,027
  7. 2019What Does BERT Look At? An Analysis of BERT's Attentioncited by 1,003
  8. 2019Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Prunedcited by 856
  9. 2020Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?cited by 599
  10. 2019ERASER: A Benchmark to Evaluate Rationalized NLP Modelscited by 530
  11. 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 476
  12. 2020Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Groundingcited by 414
20 more
  1. 2018Speaker-Follower Models for Vision-and-Language Navigationcited by 340
  2. 2019On the (In)fidelity and Sensitivity for Explanationscited by 310
  3. 2018Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigationcited by 305
  4. 2020A Recurrent Vision-and-Language BERT for Navigationcited by 302
  5. 2019Learning to Navigate Unseen Environments: Back Translation with Environmental Dropoutcited by 244
  6. 2022Towards Faithful Model Explanation in NLP: A Surveycited by 130
  7. 2019Learning to Deceive with Attention-Based Explanationscited by 111
  8. 2020Explainability in Deep Reinforcement Learningcited by 97
  9. 2021The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanationscited by 87
  10. 2020Object-and-Action Aware Model for Visual Language Navigationcited by 77
  11. 2021Vision-Language Navigation with Random Environmental Mixupcited by 70
  12. 2019Are You Looking? Grounding to Multiple Modalities in Vision-and-Language Navigationcited by 55
  13. 2020Active Visual Information Gathering for Vision-Language Navigationcited by 55
  14. 2014Extraction of Salient Sentences from Labelled Documentscited by 50
  15. 2019Transferable Representation Learning in Vision-and-Language Navigationcited by 48
  16. 2022ADAPT: Vision-Language Navigation with Modality-Aligned Action Promptscited by 45
  17. 2020Why Attentions May Not Be Interpretable?cited by 41
  18. 2021Evaluating Saliency Methods for Neural Language Modelscited by 37
  19. 2021Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classificationcited by 29
  20. 2020Evaluating Explanation Methods for Neural Machine Translationcited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026What do VLM-Based Vision-Language Navigation Models Rely on: Interpreting and Steering Policy Behaviorcited by 0