Image captioning for effective use of language models in knowledge-based visual question answering

In this investigation, we propose a solution for the author’s gender identification task called AGI-P. This task has several real-world applications across different fields, such as marketing and advertising, forensic linguistics, sociology, recommendation systems, language processing, historical analysis, education, and language learning. We created a new dataset to evaluate our proposed method. The dataset is balanced in terms of gender using a random sampling method and consists of 1944 samples in total. We use accuracy as an evaluation measure and compare the performance of the proposed solution (AGI-P) against state-of-the-art machine learning classifiers and fine-tuned pre-trained multilingual language models such as DistilBERT, mBERT, XLM-RoBERTa, and Multilingual DEBERTa. In this regard, we also propose a customized fine-tuning strategy that improves the accuracy of the pre-trained language models for the author gender identification task. Our extensive experimental studies reveal that our solution (AGI-P) outperforms the well-known machine learning classifiers and fine-tuned pre-trained multilingual language models with an accuracy level of 92.03%. Moreover, the pre-trained multilingual language models, fine-tuned with the proposed customized strategy, outperform the fine-tuned pre-trained language models using an out-of-the-box fine-tuning strategy. The codebase and the corpus will be publicly available for scholars in this area upon publication.

Korean is the native and official language spoken by Chinese-Korean people, and Weibo is a social media software with a huge number of users in China. Currently, there is few studies related to sentiment analysis of Korean-language Weibo texts posted by Chinese-Korean users. In this paper, we propose a sentiment classification method for Chinese-Korean Weibo based on pre-trained language model and transfer learning. Firstly, we crawled the Chinese-Korean Weibo data from Sina Weibo and label them with sentiment to get the Chinese-Korean Weibo sentiment analysis (CKWSA) dataset. Secondly, to solve the problem of few training samples of the Chinese-Korean Weibo sentiment analysis dataset, we fine-tune the classifier based on the pre-trained Korean language model on the Korean Twitter sentiment analysis dataset to obtain the Korean Twitter sentiment classification model; and further fine-tune the model on CKWSA dataset to get Chinese-Korean Weibo sentiment classification model. The experiments show that the proposed classification method based on pre-trained language model and transfer learning has great performance, and there is an improvement compared other baselines on the Chinese-Korean Weibo sentiment analysis dataset.

Knowledge-based visual question answering (VQA) involves answering questions that require external knowledge not present in the image. Existing methods first retrieve knowledge from external resources, then reason over the selected knowledge, the input image, and question for answer prediction. However, this two-step approach could lead to mismatches that potentially limit the VQA performance. For example, the retrieved knowledge might be noisy and irrelevant to the question, and the re-embedded knowledge features during reasoning might deviate from their original meanings in the knowledge base (KB). To address this challenge, we propose PICa, a simple yet effective method that Prompts GPT3 via the use of Image Captions, for knowledge-based VQA. Inspired by GPT-3’s power in knowledge retrieval and question answering, instead of using structured KBs as in previous work, we treat GPT-3 as an implicit and unstructured KB that can jointly acquire and process relevant knowledge. Specifically, we first convert the image into captions (or tags) that GPT-3 can understand, then adapt GPT-3 to solve the VQA task in a few-shot manner by just providing a few in-context VQA examples. We further boost performance by carefully investigating: (i) what text formats best describe the image content, and (ii) how in-context examples can be better selected and used. PICa unlocks the first use of GPT-3 for multimodal tasks. By using only 16 examples, PICa surpasses the supervised state of the art by an absolute +8.6 points on the OK-VQA dataset. We also benchmark PICa on VQAv2, where PICa also shows a decent few-shot performance.

In this paper, we aim to obtain improved attention for a visual question answering (VQA) task. It is challenging to provide supervision for attention. An observation we make is that visual explanations as obtained through class activation mappings (specifically Grad-CAM) that are meant to explain the performance of various networks could form a means of supervision. However, as the distributions of attention maps and that of Grad-CAMs differ, it would not be suitable to directly use these as a form of supervision. Rather, we propose the use of a discriminator that aims to distinguish samples of visual explanation and attention maps. The use of adversarial training of the attention regions as a two-player game between attention and explanation serves to bring the distributions of attention maps and visual explanations closer. Significantly, we observe that providing such a means of supervision also results in attention maps that are more closely related to human attention resulting in a substantial improvement over baseline stacked attention network (SAN) models. It also results in a good improvement in rank correlation metric on the VQA task. This method can also be combined with recent MCB based methods and results in consistent improvement. We also provide comparisons with other means for learning distributions such as based on Correlation Alignment (Coral), Maximum Mean Discrepancy (MMD) and Mean Square Error (MSE) losses and observe that the adversarial loss outperforms the other forms of learning the attention maps. Visualization of the results also confirms our hypothesis that attention maps improve using this form of supervision.

Antimicrobial peptides (AMPs) are vital components of innate immunotherapy. Existing approaches mainly rely on either deep learning for the automatic extraction of sequence features or traditional manual amino acid features combined with machine learning. The peptide sequence contains symmetrical sequence motifs or repetitive amino acid patterns, which may be related to the function and structure of the peptide. Recently, the advent of large language models has significantly boosted the representational power of sequence pattern features. In light of this, we present a novel AMP predictor called UniproLcad, which integrates three prominent protein language models—ESM-2, ProtBert, and UniRep—to obtain a more comprehensive representation of protein features. UniproLcad utilizes deep learning networks, encompassing the bidirectional long and short memory network (Bi-LSTM) and one-dimensional convolutional neural networks (1D-CNN), while also integrating an attention mechanism to enhance its capabilities. These deep learning frameworks, coupled with pre-trained language models, efficiently extract multi-view features from antimicrobial peptide sequences and assign attention weights to them. Through ten-fold cross-validation and independent testing, UniproLcad demonstrates competitive performance in the field of antimicrobial peptide identification. This integration of diverse language models and deep learning architectures enhances the accuracy and reliability of predicting antimicrobial peptides, contributing to the advancement of computational methods in this field.

This paper describes the models designated for the MEDIQA 2019 shared tasks by the team PANLP. We take advantages of the recent advances in pre-trained bidirectional transformer language models such as BERT (Devlin et al., 2018) and MT-DNN (Liu et al., 2019b). We find that pre-trained language models can significantly outperform traditional deep learning models. Transfer learning from the NLI task to the RQE task is also experimented, which proves to be useful in improving the results of fine-tuning MT-DNN large. A knowledge distillation process is implemented, to distill the knowledge contained in a set of models and transfer it into an single model, whose performance turns out to be comparable with that obtained by the ensemble of that set of models. Finally, for test submissions, model ensemble and a re-ranking process are implemented to boost the performances. Our models participated in all three tasks and ranked the 1st place for the RQE task, and the 2nd place for the NLI task, and also the 2nd place for the QA task.

Lying in the cross-section of computer vision and natural language processing, vision language models are capable of processing images and text at once. These models are helpful in various tasks: text generation from image and vice versa, image-text retrieval, or visual navigation. Besides building a model trained on a dataset for a task, people also study general-purpose models to utilize many datasets for multitasks. Their two primary applications are image captioning and visual question answering. For English, large datasets and foundation models are already abundant. However, for Vietnamese, they are still limited. To expand the language range, this work proposes a pretrained general-purpose image-text model named VisualRoBERTa. A dataset of 600k images with captions (translated MS COCO 2017 from English to Vietnamese) is introduced to pretrain VisualRoBERTa. The model’s architecture is built using Convolutional Neural Network and Transformer blocks. Fine-tuning VisualRoBERTa shows promising results on the ViVQA dataset with 34.49% accuracy, 0.4173 BLEU 4, and 0.4390 RougeL (in visual question answering task), and best outcomes on the sViIC dataset with 0.6685 BLEU 4, 0.6320 RougeL (in image captioning task).

With the success of down streaming task using English pre-trained language model, the pre-trained Chinese language model is also necessary to get better performance of Chinese NLP tasks. Unlike the English language, Chinese has its special characters such as glyph information. So in this article, we propose the Chinese pre-trained language model named StyleBERT which incorporate the following embedding information to enhance the savvy of language model, such as word, pinyin, five stroke and chaizi. The experiments show that the model achieves well performances on a wide range of Chinese NLP tasks.

The field of visual question answering (VQA) has seen a growing trend of integrating external knowledge sources to improve performance. However, owing to the potential incompleteness of external knowledge sources and the inherent mismatch between different forms of data, current knowledge-based visual question answering (KBVQA) techniques are still confronted with the challenge of effectively integrating and utilizing multiple heterogeneous data. To address this issue, a novel approach centered on a multi-modal semantic graph (MSG) is proposed. The MSG serves as a mechanism for effectively unifying the representation of heterogeneous data and diverse types of knowledge. Additionally, a multi-modal semantic graph knowledge reasoning model (MSG-KRM) is introduced to perform reasoning and deep fusion of image–text information and external knowledge sources. The development of the semantic graph involves extracting keywords from the image object detection information, question text, and external knowledge texts, which are then represented as symbol nodes. Three types of semantic graphs are then constructed based on the knowledge graph, including vision, question, and the external knowledge text, with non-symbol nodes added to connect these three independent graphs and marked with respective node and edge types. During the inference stage, the multi-modal semantic graph and image–text information are embedded into the feature semantic graph through three embedding methods, and a type-aware graph attention module is employed for deep reasoning. The final answer prediction is a blend of the output from the pre-trained model, graph pooling results, and the characteristics of non-symbolic nodes. The experimental results on the OK-VQA dataset show that the MSG-KRM model is superior to existing methods in terms of overall accuracy score, achieving a score of 43.58, and with improved accuracy for most subclass questions, proving the effectiveness of the proposed method.

In recent years, the attention mechanism has become a fairly popular concept and has proven to be successful in many machine learning applications. However, deep learning models do not employ supervision for these attention mechanisms which can improve the model's performance significantly. Therefore, in this paper, we tackle this limitation and propose a novel method to improve the attention mechanism by inducing "self-supervision". We devise a technique to generate desirable attention maps for any model that utilizes an attention module. This is achieved by examining the model's output for different regions sampled from the input and obtaining the attention probability distributions that enhance the proficiency of the model. The attention distributions thus obtained are used for supervision. We rely on the fact, that attenuation of the unimportant parts, allows a model to attend to more salient regions, thus strengthening the prediction accuracy. The quantitative and qualitative results published in this paper show that this method successfully improves the attention mechanism as well as the model's accuracy. In addition to the task of Visual Question Answering(VQA), we also show results on the task of Image classification and Text classification to prove that our method can be generalized to any vision and language model that uses an attention module.

Transfer learning with large pretrained transformer-based language models like BERT has become a dominating approach for most NLP tasks. Simply fine-tuning those large language models on downstream tasks or combining it with task-specific pretraining is often not robust. In particular, the performance considerably varies as the random seed changes or the number of pretraining and/or fine-tuning iterations varies, and the fine-tuned model is vulnerable to adversarial attack. We propose a simple yet effective adapter-based approach to mitigate these issues. Specifically, we insert small bottleneck layers (i.e., adapter) within each layer of a pretrained model, then fix the pretrained layers and train the adapter layers on the downstream task data, with (1) task-specific unsupervised pretraining and then (2) task-specific supervised training (e.g., classification, sequence labeling). Our experiments demonstrate that such a training scheme leads to improved stability and adversarial robustness in transfer learning to various downstream tasks.

The task of visual question answering (VQA) is receiving increasing interest from researchers in both the computer vision and natural language processing fields. Tremendous advances have been seen in the field of computer vision due to the success of deep learning, in particular on low- and midlevel tasks, such as image segmentation or object recognition. These advances have fueled researchers' confidence for tackling more complex tasks that combine vision with language and high-level reasoning. VQA is a prime example of this trend. This article presents the ongoing work in the field and the current approaches to VQA based on deep learning. VQA constitutes a test for deep visual understanding and a benchmark for general artificial intelligence (AI). While the field of VQA has seen recent successes, it remains a largely unsolved task.

We propose a model for free-form visual question answering (VQA) from human brain activity. The task of VQA is leading to an answer given an image and a question about the image. Given brain activity data measured by functional magnetic resonance imaging (fMRI) and a natural language question in terms of the viewed image, the proposed method can provide an accurate natural language answer with the VQA algorithm. Visual questions selectively approach various areas of an image such as objects and backgrounds. As a result, a more detailed understanding of the image and complex reasoning are typically needed than general image captioning models. In this paper, we propose a method of answering a given question about a viewed image from fMRI data based on the VQA algorithm. We estimate the relation between fMRI data and visual features extracted from viewed images. Based on the relationship, we convert fMRI data into visual features. Finally, the proposed method can answer to a visual question from fMRI data measured while subjects are viewing images. Experimental results show that the proposed method enables accurate answering for questions about viewed images.

In this paper, we propose a novel large scale Visual Question Answering (VQA) dataset, which aims at real environment applications. Existing VQA datasets either require high constructing labor costs or have only limited power for evaluating complicated scene understanding ability involving in VQA tasks. Moreover, most VQA datasets do not tackle scenes containing object occlusion, which could be crucial for real-world applications. In this work, we propose a synthetic multi-view VQA dataset along with a dataset generation process. We build our dataset from three real object model datasets. Each scene is observed from multiple virtual cameras, which often requires a multi-view scene understanding. Our dataset requires relatively low labor cost and in the meantime, have highly complicated visual information. In addition, our dataset can be further adapted to users’ requirements by extending the dataset setup. We evaluated two previous multi-view VQA methods on our datasets. The results show that both 3D understanding and appearance understanding is crucial to achieving high performance in our dataset, and there is still room for future methods to improve. Our dataset provides a possible way for bridging the VQA methods aiming at CG dataset with real-world applications, such as robot picking tasks.

Multiple-choice (MC) Visual Question Answering (VQA) is a similar but essentially different task to open-ended VQA because the answer options are provided. Most of existing works tackle them in a unified pipeline by solving a multi-class problem to infer the best answer from a predefined answer set. The option that matches the best answer is selected for MC VQA. Nevertheless, this violates human thinking logics. Normally, people examine the questions, answer options and the reference image before inferring a MC VQA. For MC VQA, human either rely on the question and answer options to directly deduce a correct answer if the question is not image-related, or read the question and answer options and then purposefully search for answers in a reference image. Therefore, we propose a novel approach, namely Multi-task Learning with Adaptive-attention (MTA), to simulate human logics for MC VQA. Specifically, we first fuse the answer options and question features, and then adaptively attend to the visual features for inferring a MC VQA. Furthermore, we design our model as a multi-task learning architecture by integrating the open-ended VQA task to further boost the performance of MC VQA. We evaluate our approach on two standard benchmark datasets: VQA and Visual7W and our approach sets new records on both datasets for MC VQA task, reaching 73.5% and 65.9% average accuracy respectively.