Bridging the visual gap in VLN via semantically richer instructions

• URL: http://arxiv.org/abs/2210.15565v1
• Date: Thu, 27 Oct 2022 15:58:07 GMT
• Title: Bridging the visual gap in VLN via semantically richer instructions
• Authors: Joaquin Ossand\'on, Benjamin Earle, \'Alvaro Soto
• Abstract summary: We show that state-of-the-art models are not severely affected when they receive just limited or even no visual data. We propose a new data augmentation method that fosters the inclusion of more explicit visual information.
• Score: 3.5789352263336847
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The Visual-and-Language Navigation (VLN) task requires understanding a textual instruction to navigate a natural indoor environment using only visual information. While this is a trivial task for most humans, it is still an open problem for AI models. In this work, we hypothesize that poor use of the visual information available is at the core of the low performance of current models. To support this hypothesis, we provide experimental evidence showing that state-of-the-art models are not severely affected when they receive just limited or even no visual data, indicating a strong overfitting to the textual instructions. To encourage a more suitable use of the visual information, we propose a new data augmentation method that fosters the inclusion of more explicit visual information in the generation of textual navigational instructions. Our main intuition is that current VLN datasets include textual instructions that are intended to inform an expert navigator, such as a human, but not a beginner visual navigational agent, such as a randomly initialized DL model. Specifically, to bridge the visual semantic gap of current VLN datasets, we take advantage of metadata available for the Matterport3D dataset that, among others, includes information about object labels that are present in the scenes. Training a state-of-the-art model with the new set of instructions increase its performance by 8% in terms of success rate on unseen environments, demonstrating the advantages of the proposed data augmentation method.

Related papers

• UnitedVLN: Generalizable Gaussian Splatting for Continuous Vision-Language Navigation [71.97405667493477]
  We introduce a novel, generalizable 3DGS-based pre-training paradigm, called UnitedVLN. It enables agents to better explore future environments by unitedly rendering high-fidelity 360 visual images and semantic features. UnitedVLN outperforms state-of-the-art methods on existing VLN-CE benchmarks.
  arXiv  Detail & Related papers  (2024-11-25T02:44:59Z)
• ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Models [32.24716280370563]
  ICT is a lightweight, training-free method that calculates an intervention direction to shift the model's focus towards different levels of visual information. It achieves strong performance with a small amount of data and generalizes well across different datasets and models.
  arXiv  Detail & Related papers  (2024-11-22T12:22:21Z)
• Enhancing Large Vision Language Models with Self-Training on Image Comprehension [131.14381425260706]
  We introduce Self-Training on Image (STIC), which emphasizes a self-training approach specifically for image comprehension. First, the model self-constructs a preference for image descriptions using unlabeled images. To further self-improve reasoning on the extracted visual information, we let the model reuse a small portion of existing instruction-tuning data.
  arXiv  Detail & Related papers  (2024-05-30T05:53:49Z)
• Data-efficient Large Vision Models through Sequential Autoregression [58.26179273091461]
  We develop an efficient, autoregression-based vision model on a limited dataset. We demonstrate how this model achieves proficiency in a spectrum of visual tasks spanning both high-level and low-level semantic understanding. Our empirical evaluations underscore the model's agility in adapting to various tasks, heralding a significant reduction in the parameter footprint.
  arXiv  Detail & Related papers  (2024-02-07T13:41:53Z)
• Visual Data-Type Understanding does not emerge from Scaling Vision-Language Models [31.69213233651326]
  We introduce the novel task of Visual Data-Type Identification. An extensive zero-shot evaluation of 39 vision-language models (VLMs) shows a nuanced performance landscape.
  arXiv  Detail & Related papers  (2023-10-12T17:59:30Z)
• Ignorance is Bliss: Robust Control via Information Gating [60.17644038829572]
  Informational parsimony provides a useful inductive bias for learning representations that achieve better generalization by being robust to noise and spurious correlations. We propose textitinformation gating as a way to learn parsimonious representations that identify the minimal information required for a task.
  arXiv  Detail & Related papers  (2023-03-10T18:31:50Z)
• Understanding ME? Multimodal Evaluation for Fine-grained Visual Commonsense [98.70218717851665]
  It is unclear whether the models really understand the visual scene and underlying commonsense knowledge due to limited evaluation data resources. We present a Multimodal Evaluation (ME) pipeline to automatically generate question-answer pairs to test models' understanding of the visual scene, text, and related knowledge. We then take a step further to show that training with the ME data boosts the model's performance in standard VCR evaluation.
  arXiv  Detail & Related papers  (2022-11-10T21:44:33Z)
• Leveraging Unlabeled Data for Sketch-based Understanding [11.95015190261688]
  We present a study about the use of unlabeled data to improve a sketch-based model. Our results show the superiority of sketch-BYOL, which outperforms other self-supervised approaches.
  arXiv  Detail & Related papers  (2022-04-26T18:13:30Z)
• Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training [150.35927365127176]
  We present the first pre-training and fine-tuning paradigm for vision-and-language navigation (VLN) tasks. By training on a large amount of image-text-action triplets in a self-supervised learning manner, the pre-trained model provides generic representations of visual environments and language instructions. It learns more effectively in new tasks and generalizes better in a previously unseen environment.
  arXiv  Detail & Related papers  (2020-02-25T03:08:12Z)

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.