Visual Question Answering Models Research Articles

Deep learning-based bridge damage cause estimation from multiple images using visual question answering

This paper presents a framework for estimating the cause of damage to bridge members by combining Structure from Motion (SfM) and Visual Question Answering (VQA) techniques. A VQA model was developed that uses bridge images for dataset creation and outputs the damage or member name and its existence based on the images and questions. In the developed model, the correct answer rate for questions requiring the member or damage name were 67.4 and 68.9%, respectively. The correct answer rate for questions requiring a yes/no answer was 99.1%. Based on the developed model, a damage cause estimation method was proposed. In the proposed method, the damage causes are narrowed down by inputting new questions to the VQA model, which are determined based on the surrounding images obtained via SfM and the results of the VQA model. Subsequently, the proposed method was then applied to an actual bridge and shown to be capable of determining damage and estimating its cause. The proposed method could be used to prevent damage causes from being overlooked, and practitioners could determine inspection focus areas, which could contribute to the improvement of maintenance techniques. In the future, it is expected to contribute to infrastructure diagnosis automation.

Learning the Meanings of Function Words From Grounded Language Using a Visual Question Answering Model.

Interpreting a seemingly simple function word like "or," "behind," or "more" can require logical, numerical, and relational reasoning. How are such words learned by children? Prior acquisition theories have often relied on positing a foundation of innate knowledge. Yet recent neural-network-based visual question answering models apparently can learn to use function words as part of answering questions about complex visual scenes. In this paper, we study what these models learn about function words, in the hope of better understanding how the meanings of these words can be learned by both models and children. We show that recurrent models trained on visually grounded language learn gradient semantics for function words requiring spatial and numerical reasoning. Furthermore, we find that these models can learn the meanings of logical connectives and and or without any prior knowledge of logical reasoning as well as early evidence that they are sensitive to alternative expressions when interpreting language. Finally, we show that word learning difficulty is dependent on the frequency of models' input. Our findings offer proof-of-concept evidence that it is possible to learn the nuanced interpretations of function words in a visually grounded context by using non-symbolic general statistical learning algorithms, without any prior knowledge of linguisticmeaning.

Visual Mind: Visual Question Answering (VQA) with CLIP Model

Abstract: This paper proposes a Visual Question Answering (VQA) problem using CLIP models. The proposed approach suggests an enhanced VQA-CLIP model with additional layers for better computational performance. VQA is an increasingly important task that aims to answer open-ended questions based on images. This task has numerous applications in various fields such as medicine, education, and surveillance. The VizWiz dataset, specifically designed to assist visually impaired individuals, consists of image/question pairs along with 10 answers per question, recorded by blind participants in a natural setting. The task involves predicting answers to questions and determining when a question is unanswerable. In this study, we will utilize the VizWiz dataset and employ the CLIP model with an additional linear layer, a multimodal, zero-shot model known for its efficiency in processing image and text data. By leveraging the unique capabilities of CLIP, and benchmarked against state-ofthe-art approaches. Results indicate a competitive or better performance of the VQA model.

Dual modality prompt learning for visual question-grounded answering in robotic surgery

With recent advancements in robotic surgery, notable strides have been made in visual question answering (VQA). Existing VQA systems typically generate textual answers to questions but fail to indicate the location of the relevant content within the image. This limitation restricts the interpretative capacity of the VQA models and their ability to explore specific image regions. To address this issue, this study proposes a grounded VQA model for robotic surgery, capable of localizing a specific region during answer prediction. Drawing inspiration from prompt learning in language models, a dual-modality prompt model was developed to enhance precise multimodal information interactions. Specifically, two complementary prompters were introduced to effectively integrate visual and textual prompts into the encoding process of the model. A visual complementary prompter merges visual prompt knowledge with visual information features to guide accurate localization. The textual complementary prompter aligns visual information with textual prompt knowledge and textual information, guiding textual information towards a more accurate inference of the answer. Additionally, a multiple iterative fusion strategy was adopted for comprehensive answer reasoning, to ensure high-quality generation of textual and grounded answers. The experimental results validate the effectiveness of the model, demonstrating its superiority over existing methods on the EndoVis-18 and EndoVis-17 datasets.

NExT-OOD: Overcoming Dual Multiple-Choice VQA Biases.

In recent years, multiple-choice Visual Question Answering (VQA) has become topical and achieved remarkable progress. However, most pioneer multiple-choice VQA models are heavily driven by statistical correlations in datasets, which cannot perform well on multimodal understanding and suffer from poor generalization. In this paper, we identify two kinds of spurious correlations, i.e., a Vision-Answer bias (VA bias) and a Question-Answer bias (QA bias). To systematically and scientifically study these biases, we construct a new video question answering (videoQA) benchmark NExT-OOD in OOD setting and propose a graph-based cross-sample method for bias reduction. Specifically, the NExT-OOD is designed to quantify models' generalizability and measure their reasoning ability comprehensively. It contains three sub-datasets including NExT-OOD-VA, NExT-OOD-QA, and NExT-OOD-VQA, which are designed for the VA bias, QA bias, and VA&QA bias, respectively. We evaluate several existing multiple-choice VQA models on our NExT-OOD, and illustrate that their performance degrades significantly compared with the results obtained on the original multiple-choice VQA dataset. Besides, to mitigate the VA bias and QA bias, we explicitly consider the cross-sample information and design a contrastive graph matching loss in our approach, which provides adequate debiasing guidance from the perspective of whole dataset, and encourages the model to focus on multimodal contents instead of spurious statistical regularities. Extensive experimental results illustrate that our method significantly outperforms other bias reduction strategies, demonstrating the effectiveness and generalizability of the proposed approach.

Improving Automatic VQA Evaluation Using Large Language Models

8 years after the visual question answering (VQA) task was proposed, accuracy remains the primary metric for automatic evaluation. VQA Accuracy has been effective so far in the IID evaluation setting. However, our community is undergoing a shift towards open-ended generative models and OOD evaluation. In this new paradigm, the existing VQA Accuracy metric is overly stringent and underestimates the performance of VQA systems. Thus, there is a need to develop more robust automatic VQA metrics that serve as a proxy for human judgment. In this work, we propose to leverage the in-context learning capabilities of instruction-tuned large language models (LLMs) to build a better VQA metric. We formulate VQA evaluation as an answer-rating task where the LLM is instructed to score the accuracy of a candidate answer given a set of reference answers. We demonstrate the proposed metric better correlates with human judgment compared to existing metrics across several VQA models and benchmarks. We hope wide adoption of our metric will contribute to better estimating the research progress on the VQA task. We plan to release the evaluation code and collected human judgments.

Bidirectional Contrastive Split Learning for Visual Question Answering

Visual Question Answering (VQA) based on multi-modal data facilitates real-life applications such as home robots and medical diagnoses. One significant challenge is to devise a robust decentralized learning framework for various client models where centralized data collection is refrained due to confidentiality concerns. This work aims to tackle privacy-preserving VQA by decoupling a multi-modal model into representation modules and a contrastive module, leveraging inter-module gradients sharing and inter-client weight sharing. To this end, we propose Bidirectional Contrastive Split Learning (BiCSL) to train a global multi-modal model on the entire data distribution of decentralized clients. We employ the contrastive loss that enables a more efficient self-supervised learning of decentralized modules. Comprehensive experiments are conducted on the VQA-v2 dataset based on five SOTA VQA models, demonstrating the effectiveness of the proposed method. Furthermore, we inspect BiCSL's robustness against a dual-key backdoor attack on VQA. Consequently, BiCSL shows significantly enhanced resilience when exposed to the multi-modal adversarial attack compared to the centralized learning method, which provides a promising approach to decentralized multi-modal learning.

VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models

Visual Question Answering (VQA) is a fundamental task in computer vision and natural language process fields. Although the “pre-training & finetuning” learning paradigm significantly improves the VQA performance, the adversarial robustness of such a learning paradigm has not been explored. In this paper, we delve into a new problem: using a pre-trained multimodal source model to create adversarial image-text pairs and then transferring them to attack the target VQA models. Correspondingly, we propose a novel VQATTACK model, which can iteratively generate both im- age and text perturbations with the designed modules: the large language model (LLM)-enhanced image attack and the cross-modal joint attack module. At each iteration, the LLM-enhanced image attack module first optimizes the latent representation-based loss to generate feature-level image perturbations. Then it incorporates an LLM to further enhance the image perturbations by optimizing the designed masked answer anti-recovery loss. The cross-modal joint attack module will be triggered at a specific iteration, which updates the image and text perturbations sequentially. Notably, the text perturbation updates are based on both the learned gradients in the word embedding space and word synonym-based substitution. Experimental results on two VQA datasets with five validated models demonstrate the effectiveness of the proposed VQATTACK in the transferable attack setting, compared with state-of-the-art baselines. This work reveals a significant blind spot in the “pre-training & fine-tuning” paradigm on VQA tasks. The source code can be found in the link https://github.com/ericyinyzy/VQAttack.

Cascade transformers with dynamic attention for video question answering

Visual question answering (VQA) has become a hot study topic with challenging motivation of correctly answering the videos or images questions in recent years. However, the existing VQA model mostly aimed at answering questions about images and performed poorly in the video question answering (VideoQA) domain. VideoQA needs to simultaneously consider the correlations between video frames and the dynamic information of multiple objects in video. Therefore, we propose a novel Cascade Transformers with Dynamic Attention for Video Question Answering (CTDA-QA), which aims to simultaneously solve the above considerations. Specifically, the proposed CTDA-QA model utilizes multiple transformers structure to encode videos for reasoning complex spatial and temporal information, which is different from the previous recurrent neural network methods. Besides, in order to effectively capture the dynamic information from various scenarios in videos, a flexible attention module has been proposed to explore the essential relations between objects in a dynamic timeline. Finally, to avoid spurious answers and fully explore the cross-modal relationships, a mixed-supervised learning strategy is designed for optimizing the reasoning tasks. The experiments on several benchmark video question–answer datasets clearly verify the performance and effectiveness of CTDA-QA, which contains the results in contrast to the state-of-the-art methods. Besides, the provided ablation study and visualization results further reveal the potential of CTDA-QA.

Bridging the Cross-Modality Semantic Gap in Visual Question Answering.

The objective of visual question answering (VQA) is to adequately comprehend a question and identify relevant contents in an image that can provide an answer. Existing approaches in VQA often combine visual and question features directly to create a unified cross-modality representation for answer inference. However, this kind of approach fails to bridge the semantic gap between visual and text modalities, resulting in a lack of alignment in cross-modality semantics and the inability to match key visual content accurately. In this article, we propose a model called the caption bridge-based cross-modality alignment and contrastive learning model (CBAC) to address the issue. The CBAC model aims to reduce the semantic gap between different modalities. It consists of a caption-based cross-modality alignment module and a visual-caption (V-C) contrastive learning module. By utilizing an auxiliary caption that shares the same modality as the question and has closer semantic associations with the visual, we are able to effectively reduce the semantic gap by separately matching the caption with both the question and the visual to generate pre-alignment features for each, which are then used in the subsequent fusion process. We also leverage the fact that V-C pairs exhibit stronger semantic connections compared to question-visual (Q-V) pairs to employ a contrastive learning mechanism on visual and caption pairs to further enhance the semantic alignment capabilities of single-modality encoders. Extensive experiments conducted on three benchmark datasets demonstrate that the proposed model outperforms previous state-of-the-art VQA models. Additionally, ablation experiments confirm the effectiveness of each module in our model. Furthermore, we conduct a qualitative analysis by visualizing the attention matrices to assess the reasoning reliability of the proposed model.

Prompting large language model with context and pre-answer for knowledge-based VQA

Existing studies apply Large Language Model (LLM) to knowledge-based Visual Question Answering (VQA) with encouraging results. Due to the insufficient input information, the previous methods still have shortcomings in constructing the prompt for LLM, and cannot fully activate the capacity of LLM. In addition, previous works adopt GPT-3 for inference, which has expensive costs. In this paper, we propose PCPA: a framework that Prompts LLM with Context and Pre-Answer for VQA. Specifically, we adopt a vanilla VQA model to generate in-context examples and candidate answers, and add a pre-answer selection layer to generate pre-answers. We integrate in-context examples and pre-answers into the prompt to inspire the LLM. In addition, we choose LLaMA instead of GPT-3, which is an open and free model. We build a small dataset to fine-tune the LLM. Compared to existing baselines, the PCPA improves accuracy by more than 2.1 and 1.5 on OK-VQA and A-OKVQA, respectively.

Simple contrastive learning in a self-supervised manner for robust visual question answering

Recent observations have revealed that Visual Question Answering models are susceptible to learning the spurious correlations formed by dataset biases, i.e., the language priors, instead of the intended solution. For instance, given a question and a relative image, some VQA systems are prone to provide the frequently occurring answer in the dataset while disregarding the image content. Such a preferred tendency has caused them to be brittle in real-world settings, harming the robustness of VQA models. We experimentally found that conventional VQA methods often confuse negative samples that with identical questions but different images, which results in the generation of linguistic bias. In this paper, we propose a simple contrastive learning scheme, namely SCLSM, to mitigate the above issues in a self-supervised manner. We construct several special negative samples and introduce a debiasing-aware contrastive learning approach to help the model learn more discriminative multimodal features, thus improving the ability of debiasing. The SCLSM is compatible with numerous VQA baselines. Experimental results on the widely-used public datasets VQA-CP v2 and VQA v2 validate the effectiveness of our proposed model.

Debiased Visual Question Answering via the perspective of question types

Visual Question Answering (VQA) aims to answer questions according to the given image. However, current VQA models tend to rely solely on textual information from the questions and ignore the visual information in the images to get answers, which is caused by bias that is generated during the training phase. Previous studies have shown that bias in VQA is mainly caused by the text modality, and our analysis suggests that question type is a crucial factor in bias formation. To address this bias, we proposed a self-supervised method including the Against Biased Samples(ABS) module that performs targeted debiasing by selecting samples that are prone to bias, and the Shuffle Question types(SQT) module that constructs negative samples by randomly replacing the question types of the samples selected by the ABS, to interrupting the shortcuts from question type to answer. Our approach mitigates the question-to-answer bias without using external annotations, overcoming the prior language problem. Additionally, we designed a new objective function for negative samples. Experimental results indicate that our method outperforms both self-supervised-based and supervised-based state-of-the-art approaches, achieving 70.36% accuracy on the VQA-CP v2 dataset.

Recovering Generalization via Pre-Training-Like Knowledge Distillation for Out-of-Distribution Visual Question Answering

With the emergence of large-scale multi-modal foundation models, significant improvements have been made towards Visual Question Answering (VQA) in recent years via the “Pre-training and Fine-tuning” paradigm. However, the fine-tuned VQA model, which is more specialized for the downstream training data, may fail to generalize well when there is a distribution shift between the training and test data, which is defined as the Out-of-Distribution (OOD) problem. An intuitive way to solve this problem is to transfer the common knowledge from the foundation model to the fine-tuned VQA model via knowledge distillation for better generalization. However, the generality of distilled knowledge based on the task-specific training data is questionable due to the bias between the training and test data. An ideal way is to adopt the pre-training data to distill the common knowledge shared by the training and OOD test samples, which however is impracticable due to the huge size of pre-training data. Based on the above considerations, in this paper, we propose a method, named Pre-training-like Knowledge Distillation (PKD), to imitate the pre-training feature distribution and leverage it to distill the common knowledge, which can improve the generalization performance of the fine-tuned model for OOD VQA. Specifically, we first leverage the in-domain VQA data as guidance and adopt two cross-modal feature prediction networks, which are learned under the supervision of image-text matching loss and feature divergence loss, to estimate pre-training-like vision and text features. Next, we conduct feature-level distillation by explicitly integrating the downstream VQA input features with the predicted pre-training-like features through a memory mechanism. In the meantime, we also conduct model-level distillation by constraining the image-text matching output of the downstream VQA model and the output of the foundation model for the pre-training-like image and text features. Extensive experiments on the VQA-CP v2 and VQA v2 datasets demonstrate the effectiveness of our method.

Enhancing visual question answering with a two‐way co‐attention mechanism and integrated multimodal features

AbstractIn Visual question answering (VQA), a natural language answer is generated for a given image and a question related to that image. There is a significant growth in the VQA task by applying an efficient attention mechanism. However, current VQA models use region features or object features that are not adequate to improve the accuracy of generated answers. To deal with this issue, we have used a Two‐way Co‐Attention Mechanism (TCAM), which is capable enough to fuse different visual features (region, object, and concept) from diverse perspectives. These diverse features lead to different sets of answers, and also, there is an inherent relationship between these visual features. We have developed a powerful attention mechanism that uses these two critical aspects by using both bottom‐up and top‐down TCAM to extract discriminative feature information. We have proposed a Collective Feature Integration Module (CFIM) to combine multimodal attention features and thus capture the valuable information from these visual features by employing a TCAM. Further, we have formulated a Vertical CFIM for fusing the features belonging to the same class and a Horizontal CFIM for combining the features belonging to different types, thus balancing the influence of top‐down and bottom‐up co‐attention. The experiments are conducted on two significant datasets, VQA 1.0 and VQA 2.0. On VQA 1.0, the overall accuracy of our proposed method is 71.23 on the test‐dev set and 71.94 on the test‐std set. On VQA 2.0, the overall accuracy of our proposed method is 75.89 on the test‐dev set and 76.32 on the test‐std set. The above overall accuracy clearly reflecting the superiority of our proposed TCAM based approach over the existing methods.

Self-supervised knowledge distillation in counterfactual learning for VQA

As a popular cross-modal reasoning task, Visual Question Answering (VQA) has achieved great progress in recent years. However, the issue of language bias has always affected the reliability of VQA models. To address this problem, counterfactual learning methods are proposed to learn more robust features to mitigate the bias problem. However, current counterfactual learning approaches mainly focus on generating synthesized samples and assigning answers to them, neglecting the relationship between factual and original data, which hinders robust feature learning for effective reasoning. To overcome this limitation, we propose a Self-supervised Knowledge Distillation approach in Counterfactual Learning for VQA, dubbed as VQA-SkdCL, which utilizes a self-supervised constraint to make good use of the hidden knowledge in the factual samples, enhancing the robustness of VQA models. We demonstrate the effectiveness of the proposed approach on VQA v2, VQA-CP v1, and VQA-CP v2 datasets and our approach achieves excellent performance.

StableNet: Distinguishing the hard samples to overcome language priors in visual question answering

AbstractWith the booming fields of computer vision and natural language processing, cross‐modal intersections such as visual question answering (VQA) have become very popular. However, several studies have shown that many VQA models suffer from severe language prior problems. After a series of experiments, the authors found that previous VQA models are in an unstable state, that is, when training is repeated several times on the same dataset, there are significant differences between the distributions of the predicted answers given by the models each time, and these models also perform unsatisfactorily in terms of accuracy. The reason for model instability is that some of the difficult samples bring serious interference to model training, so we design a method to measure model stability quantitatively and further propose a method that can alleviate both model imbalance and instability phenomena. Precisely, the question types are classified into simple and difficult ones different weighting measures are applied. By imposing constraints on the training process for both types of questions, the stability and accuracy of the model improve. Experimental results demonstrate the effectiveness of our method, which achieves 63.11% on VQA‐CP v2 and 75.49% with the addition of the pre‐trained model.

VQAPT: A New visual question answering model for personality traits in social media images

Visual Question Answering (VQA) for personality trait images on social media is challenging because of multiple emotions and actions with complex backgrounds in social media images. This work aims at developing a new VQA model for different personality traits (VQAPT) identification in a single image. This work considers the Big Five Factors (BFF) for personality traits namely, Openness, Conscientiousness, Extraversion, Agreeableness and Neuroticism. VQA is proposed based on the observation that multiple personality traits can be seen in a single image. We propose a model integrating text recognition and person/face recognition to derive the unique relationship between the text and the person's action in the image. Furthermore, a dynamic text-object graph for personality traits identification is constructed according to the query. For understanding a query, we explore the Contrastive Language-Image Pre-trained (CLIP) transformer encoder in this work. Since it is the first work of its kind, we have created a new dataset under this work for evaluation and the dataset is available publicly as mentioned in Section 4. The effectiveness of the proposed method is also evaluated on two benchmark datasets, namely TextVQA for VQA and PTI for personality traits identification.

Robust visual question answering via semantic cross modal augmentation

Recent advances in vision-language models have resulted in improved accuracy in visual question answering (VQA) tasks. However, their robustness remains limited when faced with out-of-distribution data containing unanswerable questions. In this study, we first construct a simple randomised VQA dataset, incorporating unanswerable questions from the VQA v2 dataset, to evaluate the robustness of a state-of-the-art VQA model. Our findings reveal that the model struggles to predict the “unknown” answer or provides inaccurate responses with high confidence scores for irrelevant questions. To address this issue without retraining the large backbone models, we propose Cross Modal Augmentation (CMA), a model-agnostic, test-time-only, multi-modal semantic augmentation technique. CMA generates multiple semantically-consistent but heterogeneous instances from the visual and textual inputs, which are then fed to the model, and the predictions are combined to achieve a more robust output. We demonstrate that implementing CMA enables the VQA model to provide more reliable answers in scenarios involving unanswerable questions, and show that the approach is generalisable across different categories of pre-trained vision language models.

Multi-modal spatial relational attention networks for visual question answering

Visual Question Answering (VQA) is a task that requires VQA model to fully understand the visual information of the image and the language information of the question, and then combine both to provide an answer. Recently, a large amount of VQA approaches focus on modeling intra- and inter-modal interactions with respect to vision and language using a deep modular co-attention network, which can achieve a good performance. Despite their benefits, they also have their limitations. First, the question representation is obtained through Glove word embeddings and Recurrent Neural Network, which may not be sufficient to capture the intricate semantics of the question features. Second, they mostly use visual appearance features extracted by Faster R-CNN to interact with language features, and they ignore important spatial relations between objects in images, resulting in incomplete use of image information. To overcome the limitations of previous methods, we propose a novel Multi-modal Spatial Relation Attention Network (MSRAN) for VQA, which can introduce spatial relationships between objects to fully utilize the image information, thus improving the performance of VQA. In order to achieve the above, we design two types of spatial relational attention modules to comprehensively explore the attention schemes: (i) Self-Attention based on Explicit Spatial Relation (SA-ESR) module that explores geometric relationships between objects explicitly; and (ii) Self-Attention based on Implicit Spatial Relation (SA-ISR) module that can capture the hidden dynamic relationships between objects by using spatial relationship. Moreover, the pre-training model BERT, which replaces Glove word embeddings and Recurrent Neural Network, is applied to MSRAN in order to obtain the better question representation. Extensive experiments on two large benchmark datasets, VQA 2.0 and GQA, demonstrate that our proposed model achieves the state-of-the-art performance.