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
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.
Forward citations
Cited by 2 Pith papers
-
TRAVEL: Training-Free Retrieval and Alignment for Vision-and-Language Navigation
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...
-
NAVCON: A Cognitively Inspired and Linguistically Grounded Corpus for Vision and Language Navigation
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.
Discussion (0). Continue with ORCID to comment.