Pith. sign in

REVIEW 2 cited by

Diagnosing Vision-and-Language Navigation: What Really Matters

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2103.16561 v2 pith:MW5EHOIL submitted 2021-03-30 cs.CV cs.AIcs.CL

classification cs.CVcs.AIcs.CL
keywords agentsnavigationtokensobjectvision-and-languagealignmentscross-modaldecisions
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Vision-and-language navigation (VLN) is a multimodal task where an agent follows natural language instructions and navigates in visual environments. Multiple setups have been proposed, and researchers apply new model architectures or training techniques to boost navigation performance. However, there still exist non-negligible gaps between machines' performance and human benchmarks. Moreover, the agents' inner mechanisms for navigation decisions remain unclear. To the best of our knowledge, how the agents perceive the multimodal input is under-studied and needs investigation. In this work, we conduct a series of diagnostic experiments to unveil agents' focus during navigation. Results show that indoor navigation agents refer to both object and direction tokens when making decisions. In contrast, outdoor navigation agents heavily rely on direction tokens and poorly understand the object tokens. Transformer-based agents acquire a better cross-modal understanding of objects and display strong numerical reasoning ability than non-Transformer-based agents. When it comes to vision-and-language alignments, many models claim that they can align object tokens with specific visual targets. We find unbalanced attention on the vision and text input and doubt the reliability of such cross-modal alignments.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. TRAVEL: Training-Free Retrieval and Alignment for Vision-and-Language Navigation

    cs.CV 2025-02 conditional novelty 6.0 of 10

    A zero-shot navigation pipeline using an LLM to extract landmarks, SigLIP to find goal panoramas, and GPT-4o grounding plus dynamic programming to rank paths achieves 88.9% nDTW on R2R-Habitat and 70% Precision@10 for...

  2. NAVCON: A Cognitively Inspired and Linguistically Grounded Corpus for Vision and Language Navigation

    cs.CL 2024-12 conditional novelty 6.0 of 10

    A new corpus adds 236,316 navigation concept annotations and 2.7 million aligned video frames to the R2R and RxR vision-language navigation datasets.

Pith tools