Unseen from Seen: Rewriting Observation-Instruction Using Foundation Models for Augmenting Vision-Language Navigation

• URL: http://arxiv.org/abs/2503.18065v1
• Date: Sun, 23 Mar 2025 13:18:17 GMT
• Title: Unseen from Seen: Rewriting Observation-Instruction Using Foundation Models for Augmenting Vision-Language Navigation
• Authors: Ziming Wei, Bingqian Lin, Yunshuang Nie, Jiaqi Chen, Shikui Ma, Hang Xu, Xiaodan Liang,
• Abstract summary: We propose a Rewriting-driven AugMentation (RAM) paradigm for Vision-Language Navigation (VLN)<n>Benefiting from our rewriting mechanism, new observation-instruction can be obtained in both simulator-free and labor-saving manners to promote generalization.<n> Experiments on both the discrete environments (R2R, REVERIE, and R4R) and continuous environments (R2R-CE) show the superior performance and impressive generalization ability of our method.
• Score: 67.31811007549489
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Data scarcity is a long-standing challenge in the Vision-Language Navigation (VLN) field, which extremely hinders the generalization of agents to unseen environments. Previous works primarily rely on additional simulator data or web-collected images/videos to improve the generalization. However, the simulator environments still face limited diversity, and the web-collected data often requires extensive labor to remove the noise. In this paper, we propose a Rewriting-driven AugMentation (RAM) paradigm for VLN, which directly creates the unseen observation-instruction pairs via rewriting human-annotated training data. Benefiting from our rewriting mechanism, new observation-instruction can be obtained in both simulator-free and labor-saving manners to promote generalization. Specifically, we first introduce Object-Enriched Observation Rewriting, where we combine Vision-Language Models (VLMs) and Large Language Models (LLMs) to derive rewritten object-enriched scene descriptions, enabling observation synthesis with diverse objects and spatial layouts via Text-to-Image Generation Models (T2IMs). Then, we propose Observation-Contrast Instruction Rewriting, which generates observation-aligned rewritten instructions by requiring LLMs to reason the difference between original and new observations. We further develop a mixing-then-focusing training strategy with a random observation cropping scheme, effectively enhancing data distribution diversity while suppressing augmentation data noise during training. Experiments on both the discrete environments (R2R, REVERIE, and R4R datasets) and continuous environments (R2R-CE dataset) show the superior performance and impressive generalization ability of our method. Code is available at https://github.com/SaDil13/VLN-RAM.

Related papers

• CAMeL: Cross-modality Adaptive Meta-Learning for Text-based Person Retrieval [22.01591564940522]
  We introduce a domain-agnostic pretraining framework based on Cross-modality Adaptive Meta-Learning (CAMeL) to enhance the model generalization capability. In particular, we develop a series of tasks that reflect the diversity and complexity of real-world scenarios. Our proposed model not only surpasses existing state-of-the-art methods on real-world benchmarks, but also showcases robustness and scalability.
  arXiv  Detail & Related papers  (2025-04-26T03:26:30Z)
• Adaptive Masking Enhances Visual Grounding [12.793586888511978]
  We propose IMAGE, Interpretative MAsking with Gaussian radiation modEling, to enhance vocabulary grounding in low-shot learning scenarios. We evaluate the efficacy of our approach on benchmark datasets, including COCO and ODinW, demonstrating its superior performance in zero-shot and few-shot tasks.
  arXiv  Detail & Related papers  (2024-10-04T05:48:02Z)
• Automated Data Visualization from Natural Language via Large Language Models: An Exploratory Study [41.84915013818794]
  The Natural Language to Visualization (NL2Vis) task aims to transform natural-language descriptions into visual representations for a grounded table. Many deep learning-based approaches have been developed for NL2Vis, but challenges persist in visualizing data sourced from unseen databases or spanning multiple tables. Taking inspiration from the remarkable generation capabilities of Large Language Models (LLMs), this paper conducts an empirical study to evaluate their potential in generating visualizations.
  arXiv  Detail & Related papers  (2024-04-26T03:25:35Z)
• Expedited Training of Visual Conditioned Language Generation via Redundancy Reduction [61.16125290912494]
  $textEVL_textGen$ is a framework designed for the pre-training of visually conditioned language generation models. We show that our approach accelerates the training of vision-language models by a factor of 5 without a noticeable impact on overall performance.
  arXiv  Detail & Related papers  (2023-10-05T03:40:06Z)
• Zero-Shot Video Moment Retrieval from Frozen Vision-Language Models [58.17315970207874]
  We propose a zero-shot method for adapting generalisable visual-textual priors from arbitrary VLM to facilitate moment-text alignment. Experiments conducted on three VMR benchmark datasets demonstrate the notable performance advantages of our zero-shot algorithm.
  arXiv  Detail & Related papers  (2023-09-01T13:06:50Z)
• Rank-N-Contrast: Learning Continuous Representations for Regression [28.926518084216607]
  Rank-N-Contrast (RNC) is a framework that learns continuous representations for regression by contrasting samples against each other based on their rankings in the target space. RNC guarantees the desired order of learned representations in accordance with the target orders. RNC achieves state-of-the-art performance, highlighting its intriguing properties including better data efficiency, robustness to spurious targets and data corruptions.
  arXiv  Detail & Related papers  (2022-10-03T19:00:38Z)
• Anticipating the Unseen Discrepancy for Vision and Language Navigation [63.399180481818405]
  Vision-Language Navigation requires the agent to follow natural language instructions to reach a specific target. The large discrepancy between seen and unseen environments makes it challenging for the agent to generalize well. We propose Unseen Discrepancy Anticipating Vision and Language Navigation (DAVIS) that learns to generalize to unseen environments via encouraging test-time visual consistency.
  arXiv  Detail & Related papers  (2022-09-10T19:04:40Z)
• Contrastive Instruction-Trajectory Learning for Vision-Language Navigation [66.16980504844233]
  A vision-language navigation (VLN) task requires an agent to reach a target with the guidance of natural language instruction. Previous works fail to discriminate the similarities and discrepancies across instruction-trajectory pairs and ignore the temporal continuity of sub-instructions. We propose a Contrastive Instruction-Trajectory Learning framework that explores invariance across similar data samples and variance across different ones to learn distinctive representations for robust navigation.
  arXiv  Detail & Related papers  (2021-12-08T06:32:52Z)
• PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning [109.84770951839289]
  We present PredRNN, a new recurrent network for learning visual dynamics from historical context. We show that our approach obtains highly competitive results on three standard datasets.
  arXiv  Detail & Related papers  (2021-03-17T08:28:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.