Multilingual Augmentation for Robust Visual Question Answering in Remote Sensing Images

• URL: http://arxiv.org/abs/2304.03844v1
• Date: Fri, 7 Apr 2023 21:06:58 GMT
• Title: Multilingual Augmentation for Robust Visual Question Answering in Remote Sensing Images
• Authors: Zhenghang Yuan, Lichao Mou, and Xiao Xiang Zhu
• Abstract summary: We propose a contrastive learning strategy for training robust RSVQA models against diverse question templates and words. Experimental results demonstrate that the proposed augmented dataset is effective in improving the robustness of the RSVQA model.
• Score: 19.99615698375829
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Aiming at answering questions based on the content of remotely sensed images, visual question answering for remote sensing data (RSVQA) has attracted much attention nowadays. However, previous works in RSVQA have focused little on the robustness of RSVQA. As we aim to enhance the reliability of RSVQA models, how to learn robust representations against new words and different question templates with the same meaning is the key challenge. With the proposed augmented dataset, we are able to obtain more questions in addition to the original ones with the same meaning. To make better use of this information, in this study, we propose a contrastive learning strategy for training robust RSVQA models against diverse question templates and words. Experimental results demonstrate that the proposed augmented dataset is effective in improving the robustness of the RSVQA model. In addition, the contrastive learning strategy performs well on the low resolution (LR) dataset.

Related papers

• The curse of language biases in remote sensing VQA: the role of spatial attributes, language diversity, and the need for clear evaluation [32.7348470366509]
  The goal of RSVQA is to answer a question formulated in natural language about a remote sensing image. The problem of language biases is often overlooked in the remote sensing community. The present work aims at highlighting the problem of language biases in RSVQA with a threefold analysis strategy.
  arXiv  Detail & Related papers  (2023-11-28T13:45:15Z)
• UNK-VQA: A Dataset and a Probe into the Abstention Ability of Multi-modal Large Models [55.22048505787125]
  This paper contributes a comprehensive dataset, called UNK-VQA. We first augment the existing data via deliberate perturbations on either the image or question. We then extensively evaluate the zero- and few-shot performance of several emerging multi-modal large models.
  arXiv  Detail & Related papers  (2023-10-17T02:38:09Z)
• Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models [59.05769810380928]
  Rephrase, Augment and Reason (RepARe) is a gradient-free framework that extracts salient details about the image using the underlying vision-language model. We show that RepARe can result in a 3.85% (absolute) increase in zero-shot accuracy on VQAv2, 6.41%, and 7.94% points increase on A-OKVQA, and VizWiz respectively.
  arXiv  Detail & Related papers  (2023-10-09T16:57:57Z)
• Improving Visual Question Answering Models through Robustness Analysis and In-Context Learning with a Chain of Basic Questions [70.70725223310401]
  This work proposes a new method that utilizes semantically related questions, referred to as basic questions, acting as noise to evaluate the robustness of VQA models. The experimental results demonstrate that the proposed evaluation method effectively analyzes the robustness of VQA models.
  arXiv  Detail & Related papers  (2023-04-06T15:32:35Z)
• From Easy to Hard: Learning Language-guided Curriculum for Visual Question Answering on Remote Sensing Data [27.160303686163164]
  Visual question answering (VQA) for remote sensing scene has great potential in intelligent human-computer interaction system. No object annotations are available in RSVQA datasets, which makes it difficult for models to exploit informative region representation. There are questions with clearly different difficulty levels for each image in the RSVQA task. A multi-level visual feature learning method is proposed to jointly extract language-guided holistic and regional image features.
  arXiv  Detail & Related papers  (2022-05-06T11:37:00Z)
• Adversarial VQA: A New Benchmark for Evaluating the Robustness of VQA Models [45.777326168922635]
  We introduce Adversarial VQA, a new large-scale VQA benchmark, collected iteratively via an adversarial human-and-model-in-the-loop procedure. We find that non-expert annotators can successfully attack SOTA VQA models with relative ease. Both large-scale pre-trained models and adversarial training methods can only achieve far lower performance than what they can achieve on the standard VQA v2 dataset.
  arXiv  Detail & Related papers  (2021-06-01T05:54:41Z)
• Analysis on Image Set Visual Question Answering [0.3359875577705538]
  We tackle the challenge of Visual Question Answering in multi-image setting. Traditional VQA tasks have focused on a single-image setting where the target answer is generated from a single image. In this report, we work with 4 approaches in a bid to improve the performance on the task.
  arXiv  Detail & Related papers  (2021-03-31T20:47:32Z)
• Learning Compositional Representation for Few-shot Visual Question Answering [93.4061107793983]
  Current methods of Visual Question Answering perform well on the answers with an amount of training data but have limited accuracy on the novel ones with few examples. We propose to extract the attributes from the answers with enough data, which are later composed to constrain the learning of the few-shot ones. Experimental results on the VQA v2.0 validation dataset demonstrate the effectiveness of our proposed attribute network.
  arXiv  Detail & Related papers  (2021-02-21T10:16:24Z)
• Contrast and Classify: Training Robust VQA Models [60.80627814762071]
  We propose a novel training paradigm (ConClaT) that optimize both cross-entropy and contrastive losses. We find that optimizing both losses -- either alternately or jointly -- is key to effective training.
  arXiv  Detail & Related papers  (2020-10-13T00:23:59Z)
• Structured Multimodal Attentions for TextVQA [57.71060302874151]
  We propose an end-to-end structured multimodal attention (SMA) neural network to mainly solve the first two issues above. SMA first uses a structural graph representation to encode the object-object, object-text and text-text relationships appearing in the image, and then designs a multimodal graph attention network to reason over it. Our proposed model outperforms the SoTA models on TextVQA dataset and two tasks of ST-VQA dataset among all models except pre-training based TAP.
  arXiv  Detail & Related papers  (2020-06-01T07:07:36Z)

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.