Evaluating Multimodal Representations on Visual Semantic Textual Similarity

Multimodal representation learning has shown promising improvements on various vision-language tasks (e.g., image-text retrieval, visual question answering, etc) and has significantly advanced the development of multimedia information systems. Most existing methods excel at building global-level alignment between vision and language while lacking effective fine-grained image-text interaction. In this paper, we propose a jointly masked multimodal modeling method to learn fine-grained multimodal representations. Our method performs joint masking on image-text input and integrates both implicit and explicit targets for the masked signals to recover. The implicit target provides a unified and debiased objective for vision and language, where the model predicts latent multimodal representations of the unmasked input. The explicit target further enriches the multimodal representations by recovering high-level and semantically meaningful information: momentum visual features of image patches and concepts of word tokens. Through such a masked modeling process, our model not only learns fine-grained multimodal interaction, but also avoids the semantic gap between high-level representations and low-or mid-level prediction targets (e.g., image pixels, discrete vision tokens), thus producing semantically rich multimodal representations that perform well on both zero-shot and fine-tuned settings. Our pre-trained model (named MAMO) achieves state-of-the-art performance on various downstream vision-language tasks, including image-text retrieval, visual question answering, visual reasoning, and weakly-supervised visual grounding.

Semantic Similarity is one of the highest levels of NLP. STS has significant advantages in NLP applications like information retrieval, information extraction, text summarization, data mining, machine translation, and other tasks. This research aims to present a deep learning approach for capturing semantic textual similarity (STS) in the Guragigna. The methodology involves collecting a Guragigna language corpus and preprocessing the text data and text representation is done using the Universal Sentence Encoder (USE), along with word embedding techniques including Word2Vec and GloVe and mean Square Error (MSE) is used to measure the performance. In the experimentation phase, models like LSTM, Bidirectional RNN, GRU, and Stacked RNN are trained and evaluated using different embedding techniques. The results demonstrate the efficacy of the developed models in capturing semantic textual similarity in the Guragigna language. Across different embedding techniques, including Word2Vec, GloVe, and USE, the Bidirectional RNN model with USE embedding achieves the lowest MSE of 0.0950 and the highest accuracy of 0.9244. GloVe and Word2Vec embedding also show competitive performance with slightly higher MSE and lower accuracy. The Universal Sentence Encoder consistently emerges as the top-performing embedding across all RNN architectures. The research results demonstrate the effectiveness of LSTM, GRU, Bi RNN, and Stacked RNN models in measuring semantic textual similarity in the Guragigna language.

Recently, vision-and-language grounding problems, e.g., image captioning and visual question answering (VQA), has attracted extensive interests from both academic and industrial worlds. However, given the similarity of these tasks, the efforts to obtain better results by combining the merits of their algorithms are not well studied. Inspired by the recent success of federated learning, we propose a federated learning framework to obtain various types of image representations from different tasks, which are then fused together to form fine-grained image representations. The representations merge useful features from different vision-and-language grounding problems, and are thus much more powerful than the original representations alone in individual tasks. To learn such image representations, we propose the Aligning, Integrating and Mapping Network (aimNet). The aimNet is validated on three federated learning settings, which include horizontal federated learning, vertical federated learning, and federated transfer learning. Experiments of aimNet-based federated learning framework on two representative tasks, i.e., image captioning and VQA, demonstrate the effective and universal improvements of all metrics over the baselines. In image captioning, we are able to get 14% and 13% relative gain on the task-specific metrics CIDEr and SPICE, respectively. In VQA, we could also boost the performance of strong baselines by up to 3%.

Visual Question Answering (VQA) has benefited from increasingly sophisticated models, but has not enjoyed the same level of engagement in terms of data creation. In this paper, we propose a method that automatically derives VQA examples at volume, by leveraging the abundance of existing image-caption annotations combined with neural models for textual question generation. We show that the resulting data is of high-quality. VQA models trained on our data improve state-of-the-art zero-shot accuracy by double digits and achieve a level of robustness that lacks in the same model trained on human-annotated VQA data.

Integrating outside knowledge for reasoning in visio-linguistic tasks such as visual question answering (VQA) is an open problem. Given that pretrained language models have been shown to include world knowledge, we propose to use a unimodal (text-only) train and inference procedure based on automatic off-the-shelf captioning of images and pretrained language models. More specifically, we verbalize the image contents and allow language models to better leverage their implicit knowledge to solve knowledge-intensive tasks. Focusing on a visual question answering task which requires external knowledge (OK-VQA), our contributions are: (i) a text-only model that outperforms pretrained multimodal (image-text) models of comparable number of parameters; (ii) confirmation that our text-only method is specially effective for tasks requiring external knowledge, as it is less effective in standard a VQA task (VQA 2.0); and (iii) our method attains results in the state-of-the-art when increasing the size of the language model. We also significantly outperform current multimodal systems, even though augmented with external knowledge. Our qualitative analysis on OK-VQA reveals that automatic captions often fail to capture relevant information in the images, which seems to be balanced by the better inference ability of the text-only language models. Our work opens up possibilities to further improve inference in visio-linguistic tasks.

Image captioning and visual question answering are typical tasks that connect computer vision and natural language processing. Both of them need to effectively represent the visual content using computer vision methods and smoothly process the text sentence using natural language processing skills. The key problem of these two tasks is to infer the target result based on the interactive understanding of the word sequence and the image. Though they practically use similar algorithms, they are studied independently in the past few years. In this article, we attempt to exploit the mutual correlation between these two tasks. We propose the first VQA-improved image-captioning method that transfers the knowledge learned from the VQA corpora to the image-captioning task. A VQA model is first pretrained on image--question--answer instances. Then, the pretrained VQA model is used to extract VQA-grounded semantic representations according to selected free-form open-ended visual question--answer pairs. The VQA-grounded features are complementary to the visual features, because they interpret images from a different perspective. We incorporate the VQA model into the image-captioning model by adaptively fusing the VQA-grounded feature and the attended visual feature. We show that such simple VQA-improved image-captioning (VQA-IIC) models perform better than conventional image-captioning methods on large-scale public datasets.

Deep learning has made tremendous success in computer vision, natural language processing and even visual-semantic learning, which requires a huge amount of labeled training data. Nevertheless, the goal of human-level intelligence is to enable a model to quickly obtain an in-depth understanding given a small number of samples, especially with heterogeneity in the multi-modal scenarios such as visual question answering and image captioning. In this paper, we study the few-shot visual-semantic learning and present the Hierarchical Graph ATtention network (HGAT). This two-stage network models the intra- and inter-modal relationships with limited image-text samples. The main contributions of HGAT can be summarized as follows: 1) it sheds light on tackling few-shot multi-modal learning problems, which focuses primarily, but not exclusively on visual and semantic modalities, through better exploitation of the intra-relationship of each modality and an attention-based co-learning framework between modalities using a hierarchical graph-based architecture; 2) it achieves superior performance on both visual question answering and image captioning in the few-shot setting; 3) it can be easily extended to the semi-supervised setting where image-text samples are partially unlabeled. We show via extensive experiments that HGAT delivers state-of-the-art performance on three widely-used benchmarks of two visual-semantic learning tasks.

One of the most overwhelming and exhilarating advancements in the field of intelligent systems has been the introduction of visual question answering (VQA), a new and exciting problem that makes use of natural language processing and computer vision for measuring the ability of a system for image understanding and generating inferences beyond object recognition, segmentation and image captioning. One of the primary goals of research in visual-based artificial intelligence is to design systems that can understand and reply to questions about visual data. The first part of the study very vividly presents numerous diversified as well as diagnostic datasets testing different visual reasoning abilities, while the second part of the study details a plethora of the recently developed approaches for VQA. Finally, a qualitative comparison of the diversity present in the various approaches has been done that can serve as an important benchmark for analysing and comparing the different characteristics and applications of these algorithms and datasets that can prove to be helpful to someone new to the field of VQA and its community.

Adversarial examples have been successfully generated for various image classification models. Recently, several methods have been proposed to generate adversarial examples for more sophisticated tasks such as image captioning and visual question answering (VQA). In this paper, we propose a targeted adversarial attack for VQA where the noise is added only to the background pixels of the image keeping the rest of the image unchanged. The experiments are done on two state-of-the-art VQA systems: End-to-End Neural Module Network (N2NMN) and Memory, Attention and Composition Network (MAC network) and three datasets: SHAPES, CLEVR, and VQA v2.0. We combine validation and test sets of SHAPES, and select 1000 image-question pairs from CLEVR validation set. For VQA v2.0, we select 500 image-question pairs from the validation set for experimentation. We study the proposed attack under two different settings: same-category and different-category; referring to whether or not the target adversarial answer lies in the same category as the original answer. For CLEVR, the proposed attack achieves 100% success rate for both the models under same-category setting and success rate of 22.3% for N2NMN and 73.9% for MAC network under different-category setting. For SHAPES, the proposed attack achieves success rate of 68.9% for N2NMN. The proposed attack also achieves high success rate for same-category setting in VQA v2.0. Furthermore, we give strong rationale behind the robustness of N2NMN to different-category attack.

Self-attention (SA) network has shown profound value in image captioning. In this paper, we improve SA from two aspects to promote the performance of image captioning. First, we propose Normalized Self-Attention (NSA), a reparameterization of SA that brings the benefits of normalization inside SA. While normalization is previously only applied outside SA, we introduce a novel normalization method and demonstrate that it is both possible and beneficial to perform it on the hidden activations inside SA. Second, to compensate for the major limit of Transformer that it fails to model the geometry structure of the input objects, we propose a class of Geometry-aware Self-Attention (GSA) that extends SA to explicitly and efficiently consider the relative geometry relations between the objects in the image. To construct our image captioning model, we combine the two modules and apply it to the vanilla self-attention network. We extensively evaluate our proposals on MS-COCO image captioning dataset and superior results are achieved when comparing to state-of-the-art approaches. Further experiments on three challenging tasks, i.e. video captioning, machine translation, and visual question answering, show the generality of our methods.

Deep learning methods have revolutionized speech recognition, image recognition, and natural language processing since 2010. Each of these tasks involves a single modality in their input signals. However, many applications in the artificial intelligence field involve multiple modalities. Therefore, it is of broad interest to study the more difficult and complex problem of modeling and learning across multiple modalities. In this paper, we provide a technical review of available models and learning methods for multimodal intelligence. The main focus of this review is the combination of vision and natural language modalities, which has become an important topic in both the computer vision and natural language processing research communities. This review provides a comprehensive analysis of recent works on multimodal deep learning from three perspectives: learning multimodal representations, fusing multimodal signals at various levels, and multimodal applications. Regarding multimodal representation learning, we review the key concepts of embedding, which unify multimodal signals into a single vector space and thereby enable cross-modality signal processing. We also review the properties of many types of embeddings that are constructed and learned for general downstream tasks. Regarding multimodal fusion, this review focuses on special architectures for the integration of representations of unimodal signals for a particular task. Regarding applications, selected areas of a broad interest in the current literature are covered, including image-to-text caption generation, text-to-image generation, and visual question answering. We believe that this review will facilitate future studies in the emerging field of multimodal intelligence for related communities.

In natural language processing (NLP) tasks, computing semantic textual similarity (STS) is crucial for capturing nuanced semantic differences in text. Traditional word vector methods, such as Word2Vec and GloVe, as well as deep learning models like BERT, face limitations in handling context dependency and polysemy and present challenges in computational resources and real-time processing. To address these issues, this paper introduces two novel methods. First, a sentence embedding generation method based on Kullback–Leibler Divergence (KLD) optimization is proposed, which enhances semantic differentiation between sentence vectors, thereby improving the accuracy of textual similarity computation. Second, this study proposes a framework incorporating RoBERTa knowledge distillation, which integrates the deep semantic insights of the RoBERTa model with prior methodologies to enhance sentence embeddings while preserving computational efficiency. Additionally, the study extends its contributions to sentiment analysis tasks by leveraging the enhanced embeddings for classification. The sentiment analysis experiments, conducted using a Stochastic Gradient Descent (SGD) classifier on the ACL IMDB dataset, demonstrate the effectiveness of the proposed methods, achieving high precision, recall, and F1 score metrics. To further augment model accuracy and efficacy, a feature selection approach is introduced, specifically through the Dynamic Principal Component Selection (DPCS) algorithm. The DPCS method autonomously identifies and prioritizes critical features, thus enriching the expressive capacity of sentence vectors and significantly advancing the accuracy of similarity computations. Experimental results demonstrate that our method outperforms existing methods in semantic similarity computation on the SemEval-2016 dataset. When evaluated using cosine similarity of average vectors, our model achieved a Pearson correlation coefficient (τ) of 0.470, a Spearman correlation coefficient (ρ) of 0.481, and a mean absolute error (MAE) of 2.100. Compared to traditional methods such as Word2Vec, GloVe, and FastText, our method significantly enhances similarity computation accuracy. Using TF-IDF-weighted cosine similarity evaluation, our model achieved a τ of 0.528, ρ of 0.518, and an MAE of 1.343. Additionally, in the cosine similarity assessment leveraging the Dynamic Principal Component Smoothing (DPCS) algorithm, our model achieved a τ of 0.530, ρ of 0.518, and an MAE of 1.320, further demonstrating the method’s effectiveness and precision in handling semantic similarity. These results indicate that our proposed method has high relevance and low error in semantic textual similarity tasks, thereby better capturing subtle semantic differences between texts.

Semantic textual similarity is the basis of countless applications and plays an important role in diverse areas, such as information retrieval, plagiarism detection, information extraction and machine translation. This article proposes an innovative word embedding-based system devoted to calculate the semantic similarity in Arabic sentences. The main idea is to exploit vectors as word representations in a multidi-mensional space in order to capture the semantic and syntactic properties of words. IDF weighting and Part-of-Speech tagging are applied on the examined sentences to support the identification of words that are highly descriptive in each sentence. The performance of our proposed system is confirmed through the Pearson correlation between our assigned semantic similarity scores and human judgments.

Soravit Changpinyo, Bo Pang, Piyush Sharma, Radu Soricut. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

We propose a technique for producing `visual explanations' for decisions from a large class of Convolutional Neural Network (CNN)-based models, making them more transparent. Our approach - Gradient-weighted Class Activation Mapping (Grad-CAM), uses the gradients of any target concept (say logits for `dog' or even a caption), flowing into the final convolutional layer to produce a coarse localization map highlighting the important regions in the image for predicting the concept. Unlike previous approaches, Grad- CAM is applicable to a wide variety of CNN model-families: (1) CNNs with fully-connected layers (e.g. VGG), (2) CNNs used for structured outputs (e.g. captioning), (3) CNNs used in tasks with multi-modal inputs (e.g. visual question answering) or reinforcement learning, without architectural changes or re-training. We combine Grad-CAM with existing fine-grained visualizations to create a high-resolution class-discriminative visualization, Guided Grad-CAM, and apply it to image classification, image captioning, and visual question answering (VQA) models, including ResNet-based architectures. In the context of image classification models, our visualizations (a) lend insights into failure modes of these models (showing that seemingly unreasonable predictions have reasonable explanations), (b) outperform previous methods on the ILSVRC-15 weakly-supervised localization task, (c) are more faithful to the underlying model, and (d) help achieve model generalization by identifying dataset bias. For image captioning and VQA, our visualizations show even non-attention based models can localize inputs. Finally, we design and conduct human studies to measure if Grad-CAM explanations help users establish appropriate trust in predictions from deep networks and show that Grad-CAM helps untrained users successfully discern a `stronger' deep network from a `weaker' one even when both make identical predictions. Our code is available at https: //github.com/ramprs/grad-cam/ along with a demo on CloudCV [2] and video at youtu.be/COjUB9Izk6E.