The recent surge of interest surrounding Multimodal Neural Networks (MM-NN) is attributed to their ability to effectively process and integrate multiscale information from diverse data sources. MM-NNs extract and fuse features from multiple modalities using adequate unimodal backbones and specific fusion networks. Although this helps strengthen the multimodal information representation, designing such networks is labor-intensive. It requires tuning the architectural parameters of the unimodal backbones, choosing the fusing point, and selecting the operations for fusion. Furthermore, multimodality AI is emerging as a cutting-edge option in Internet of Things (IoT) systems where inference latency and energy consumption are critical metrics in addition to accuracy. In this paper, we propose Harmonic-NAS, a framework for the joint optimization of unimodal backbones and multimodal fusion networks with hardware awareness on resource-constrained devices. Harmonic-NAS involves a two-tier optimization approach for the unimodal backbone architectures and fusion strategy and operators. By incorporating the hardware dimension into the optimization, evaluation results on various devices and multimodal datasets have demonstrated the superiority of Harmonic-NAS over state-of-the-art approaches achieving up to 10.9% accuracy improvement, 1.91x latency reduction, and 2.14x energy efficiency gain.
Modern Web systems such as social media and e-commerce contain rich contents expressed in images and text. Leveraging information from multi-modalities can improve the performance of machine learning tasks such as classification and recommendation. In this paper, we propose the Cross-Modality Attention Contrastive Language-Image Pre-training (CMA-CLIP), a new framework which unifies two types of cross-modality attentions, sequence-wise attention and modality-wise attention, to effectively fuse information from image and text pairs. The sequence-wise attention enables the framework to capture the fine-grained relationship between image patches and text tokens, while the modality-wise attention weighs each modality by its relevance to the downstream tasks. In addition, by adding task specific modality-wise attentions and multilayer perceptrons, our proposed framework is capable of performing multi-task classification with multi-modalities. We conduct experiments on a Major Retail Website Product Attribute (MRWPA) dataset and two public datasets, Food101 and Fashion-Gen. The results show that CMA-CLIP outperforms the pre-trained and fine-tuned CLIP by an average of 11.9% in recall at the same level of precision on the MRWPA dataset for multi-task classification. It also surpasses the state-of-the-art method on Fashion-Gen Dataset by 5.5% in accuracy and achieves competitive performance on Food101 Dataset. Through detailed ablation studies, we further demonstrate the effectiveness of both cross-modality attention modules and our method's robustness against noise in image and text inputs, which is a common challenge in practice.
The modern digital world is becoming more and more multimodal. Looking on the internet, images are often associated with the text, so classification problems with these two modalities are very common. In this paper, we examine multimodal classification using textual information and visual representations of the same concept. We investigate two main basic methods to perform multimodal fusion and adapt them with stacking techniques to better handle this type of problem. Here, we use UPMC Food-101, which is a difficult and noisy multimodal dataset that well represents this category of multimodal problems. Our results show that the proposed early fusion technique combined with a stacking-based approach exceeds the state of the art on the dataset used.
Fine-grained image classification is a challenging task due to the presence of hierarchical coarse-to-fine-grained distribution in the dataset. Generally, parts are used to discriminate various objects in fine-grained datasets, however, not all parts are beneficial and indispensable. In recent years, natural language descriptions are used to obtain information on discriminative parts of the object. This paper leverages on natural language description and proposes a strategy for learning the joint representation of natural language description and images using a two-branch network with multiple layers to improve the fine-grained classification task. Extensive experiments show that our approach gains significant improvements in accuracy for the fine-grained image classification task. Furthermore, our method achieves new state-of-the-art results on the CUB-200-2011 dataset.
Memes on the Internet are often harmless and sometimes amusing. However, by using certain types of images, text, or combinations of both, the seemingly harmless meme becomes a multimodal type of hate speech -- a hateful meme. The Hateful Memes Challenge is a first-of-its-kind competition which focuses on detecting hate speech in multimodal memes and it proposes a new data set containing 10,000+ new examples of multimodal content. We utilize VisualBERT -- which meant to be the BERT of vision and language -- that was trained multimodally on images and captions and apply Ensemble Learning. Our approach achieves 0.811 AUROC with an accuracy of 0.765 on the challenge test set and placed third out of 3,173 participants in the Hateful Memes Challenge.
Price prediction is one of the examples related to forecasting tasks and is a project based on data science. Price prediction analyzes data and predicts the cost of new products. The goal of this research is to achieve an arrangement to predict the price of a cellphone based on its specifications. So, five deep learning models are proposed to predict the price range of a cellphone, one unimodal and four multimodal approaches. The multimodal methods predict the prices based on the graphical and non-graphical features of cellphones that have an important effect on their valorizations. Also, to evaluate the efficiency of the proposed methods, a cellphone dataset has been gathered from GSMArena. The experimental results show 88.3% F1-score, which confirms that multimodal learning leads to more accurate predictions than state-of-the-art techniques.
Multimedia content in social media platforms provides significant information during disaster events. The types of information shared include reports of injured or deceased people, infrastructure damage, and missing or found people, among others. Although many studies have shown the usefulness of both text and image content for disaster response purposes, the research has been mostly focused on analyzing only the text modality in the past. In this paper, we propose to use both text and image modalities of social media data to learn a joint representation using state-of-the-art deep learning techniques. Specifically, we utilize convolutional neural networks to define a multimodal deep learning architecture with a modality-agnostic shared representation. Extensive experiments on real-world disaster datasets show that the proposed multimodal architecture yields better performance than models trained using a single modality (e.g., either text or image).