Hateful memes are a growing menace on social media. While the image and its corresponding text in a meme are related, they do not necessarily convey the same meaning when viewed individually. Hence, detecting hateful memes requires careful consideration of both visual and textual information. Multimodal pre-training can be beneficial for this task because it effectively captures the relationship between the image and the text by representing them in a similar feature space. Furthermore, it is essential to model the interactions between the image and text features through intermediate fusion. Most existing methods either employ multimodal pre-training or intermediate fusion, but not both. In this work, we propose the Hate-CLIPper architecture, which explicitly models the cross-modal interactions between the image and text representations obtained using Contrastive Language-Image Pre-training (CLIP) encoders via a feature interaction matrix (FIM). A simple classifier based on the FIM representation is able to achieve state-of-the-art performance on the Hateful Memes Challenge (HMC) dataset with an AUROC of 85.8, which even surpasses the human performance of 82.65. Experiments on other meme datasets such as Propaganda Memes and TamilMemes also demonstrate the generalizability of the proposed approach. Finally, we analyze the interpretability of the FIM representation and show that cross-modal interactions can indeed facilitate the learning of meaningful concepts. The code for this work is available at https://github.com/gokulkarthik/hateclipper.
In this study, we propose feature extraction for multimodal meme classification using Deep Learning approaches. A meme is usually a photo or video with text shared by the young generation on social media platforms that expresses a culturally relevant idea. Since they are an efficient way to express emotions and feelings, a good classifier that can classify the sentiment behind the meme is important. To make the learning process more efficient, reduce the likelihood of overfitting, and improve the generalizability of the model, one needs a good approach for joint feature extraction from all modalities. In this work, we proposed to use different multimodal neural network approaches for multimodal feature extraction and use the extracted features to train a classifier to identify the sentiment in a meme.
The step function is one of the simplest and most natural activation functions for deep neural networks (DNNs). As it counts 1 for positive variables and 0 for others, its intrinsic characteristics (e.g., discontinuity and no viable information of subgradients) impede its development for several decades. Even if there is an impressive body of work on designing DNNs with continuous activation functions that can be deemed as surrogates of the step function, it is still in the possession of some advantageous properties, such as complete robustness to outliers and being capable of attaining the best learning-theoretic guarantee of predictive accuracy. Hence, in this paper, we aim to train DNNs with the step function used as an activation function (dubbed as 0/1 DNNs). We first reformulate 0/1 DNNs as an unconstrained optimization problem and then solve it by a block coordinate descend (BCD) method. Moreover, we acquire closed-form solutions for sub-problems of BCD as well as its convergence properties. Furthermore, we also integrate $\ell_{2,0}$-regularization into 0/1 DNN to accelerate the training process and compress the network scale. As a result, the proposed algorithm has a high performance on classifying MNIST and Fashion-MNIST datasets. As a result, the proposed algorithm has a desirable performance on classifying MNIST, FashionMNIST, Cifar10, and Cifar100 datasets.
In this paper we describe our work towards building a generic framework for both multi-modal embedding and multi-label binary classification tasks, while participating in task 5 (Multimedia Automatic Misogyny Identification) of SemEval 2022 competition. Since pretraining deep models from scratch is a resource and data hungry task, our approach is based on three main strategies. We combine different state-of-the-art architectures to capture a wide spectrum of semantic signals from the multi-modal input. We employ a multi-task learning scheme to be able to use multiple datasets from the same knowledge domain to help increase the model's performance. We also use multiple objectives to regularize and fine tune different system components.
The spread of fake news, propaganda, misinformation, disinformation, and harmful content online raised concerns among social media platforms, government agencies, policymakers, and society as a whole. This is because such harmful or abusive content leads to several consequences to people such as physical, emotional, relational, and financial. Among different harmful content \textit{trolling-based} online content is one of them, where the idea is to post a message that is provocative, offensive, or menacing with an intent to mislead the audience. The content can be textual, visual, a combination of both, or a meme. In this study, we provide a comparative analysis of troll-based memes classification using the textual, visual, and multimodal content. We report several interesting findings in terms of code-mixed text, multimodal setting, and combining an additional dataset, which shows improvements over the majority baseline.
Building models that can be rapidly adapted to novel tasks using only a handful of annotated examples is an open challenge for multimodal machine learning research. We introduce Flamingo, a family of Visual Language Models (VLM) with this ability. We propose key architectural innovations to: (i) bridge powerful pretrained vision-only and language-only models, (ii) handle sequences of arbitrarily interleaved visual and textual data, and (iii) seamlessly ingest images or videos as inputs. Thanks to their flexibility, Flamingo models can be trained on large-scale multimodal web corpora containing arbitrarily interleaved text and images, which is key to endow them with in-context few-shot learning capabilities. We perform a thorough evaluation of our models, exploring and measuring their ability to rapidly adapt to a variety of image and video tasks. These include open-ended tasks such as visual question-answering, where the model is prompted with a question which it has to answer; captioning tasks, which evaluate the ability to describe a scene or an event; and close-ended tasks such as multiple-choice visual question-answering. For tasks lying anywhere on this spectrum, a single Flamingo model can achieve a new state of the art with few-shot learning, simply by prompting the model with task-specific examples. On numerous benchmarks, Flamingo outperforms models fine-tuned on thousands of times more task-specific data.
Social media platforms often act as breeding grounds for various forms of trolling or malicious content targeting users or communities. One way of trolling users is by creating memes, which in most cases unites an image with a short piece of text embedded on top of it. The situation is more complex for multilingual(e.g., Tamil) memes due to the lack of benchmark datasets and models. We explore several models to detect Troll memes in Tamil based on the shared task, "Troll Meme Classification in DravidianLangTech2022" at ACL-2022. We observe while the text-based model MURIL performs better for Non-troll meme classification, the image-based model VGG16 performs better for Troll-meme classification. Further fusing these two modalities help us achieve stable outcomes in both classes. Our fusion model achieved a 0.561 weighted average F1 score and ranked second in this task.
Hateful meme detection is a new multimodal task that has gained significant traction in academic and industry research communities. Recently, researchers have applied pre-trained visual-linguistic models to perform the multimodal classification task, and some of these solutions have yielded promising results. However, what these visual-linguistic models learn for the hateful meme classification task remains unclear. For instance, it is unclear if these models are able to capture the derogatory or slurs references in multimodality (i.e., image and text) of the hateful memes. To fill this research gap, this paper propose three research questions to improve our understanding of these visual-linguistic models performing the hateful meme classification task. We found that the image modality contributes more to the hateful meme classification task, and the visual-linguistic models are able to perform visual-text slurs grounding to a certain extent. Our error analysis also shows that the visual-linguistic models have acquired biases, which resulted in false-positive predictions.
Discriminative self-supervised learning allows training models on any random group of internet images, and possibly recover salient information that helps differentiate between the images. Applied to ImageNet, this leads to object centric features that perform on par with supervised features on most object-centric downstream tasks. In this work, we question if using this ability, we can learn any salient and more representative information present in diverse unbounded set of images from across the globe. To do so, we train models on billions of random images without any data pre-processing or prior assumptions about what we want the model to learn. We scale our model size to dense 10 billion parameters to avoid underfitting on a large data size. We extensively study and validate our model performance on over 50 benchmarks including fairness, robustness to distribution shift, geographical diversity, fine grained recognition, image copy detection and many image classification datasets. The resulting model, not only captures well semantic information, it also captures information about artistic style and learns salient information such as geolocations and multilingual word embeddings based on visual content only. More importantly, we discover that such model is more robust, more fair, less harmful and less biased than supervised models or models trained on object centric datasets such as ImageNet.
Memes are prevalent on the internet and continue to grow and evolve alongside our culture. An automatic understanding of memes propagating on the internet can shed light on the general sentiment and cultural attitudes of people. In this work, we present team BLUE's solution for the second edition of the MEMOTION shared task. We showcase two approaches for meme classification (i.e. sentiment, humour, offensive, sarcasm and motivation levels) using a text-only method using BERT, and a Multi-Modal-Multi-Task transformer network that operates on both the meme image and its caption to output the final scores. In both approaches, we leverage state-of-the-art pretrained models for text (BERT, Sentence Transformer) and image processing (EfficientNetV4, CLIP). Through our efforts, we obtain first place in task A, second place in task B and third place in task C. In addition, our team obtained the highest average score for all three tasks.
Hateful and offensive content detection has been extensively explored in a single modality such as text. However, such toxic information could also be communicated via multimodal content such as online memes. Therefore, detecting multimodal hateful content has recently garnered much attention in academic and industry research communities. This paper aims to contribute to this emerging research topic by proposing DisMultiHate, which is a novel framework that performed the classification of multimodal hateful content. Specifically, DisMultiHate is designed to disentangle target entities in multimodal memes to improve hateful content classification and explainability. We conduct extensive experiments on two publicly available hateful and offensive memes datasets. Our experiment results show that DisMultiHate is able to outperform state-of-the-art unimodal and multimodal baselines in the hateful meme classification task. Empirical case studies were also conducted to demonstrate DisMultiHate's ability to disentangle target entities in memes and ultimately showcase DisMultiHate's explainability of the multimodal hateful content classification task.
A meme is an part of media created to share an opinion or emotion across the internet. Due to its popularity, memes have become the new forms of communication on social media. However, due to its nature, they are being used in harmful ways such as trolling and cyberbullying progressively. Various data modelling methods create different possibilities in feature extraction and turning them into beneficial information. The variety of modalities included in data plays a significant part in predicting the results. We try to explore the significance of visual features of images in classifying memes. Memes are a blend of both image and text, where the text is embedded into the image. We try to incorporate the memes as troll and non-trolling memes based on the images and the text on them. However, the images are to be analysed and combined with the text to increase performance. Our work illustrates different textual analysis methods and contrasting multimodal methods ranging from simple merging to cross attention to utilising both worlds' - best visual and textual features. The fine-tuned cross-lingual language model, XLM, performed the best in textual analysis, and the multimodal transformer performs the best in multimodal analysis.
Tamil is a Dravidian language that is commonly used and spoken in the southern part of Asia. In the era of social media, memes have been a fun moment in the day-to-day life of people. Here, we try to analyze the true meaning of Tamil memes by categorizing them as troll and non-troll. We propose an ingenious model comprising of a transformer-transformer architecture that tries to attain state-of-the-art by using attention as its main component. The dataset consists of troll and non-troll images with their captions as text. The task is a binary classification task. The objective of the model is to pay more attention to the extracted features and to ignore the noise in both images and text.
State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories. This restricted form of supervision limits their generality and usability since additional labeled data is needed to specify any other visual concept. Learning directly from raw text about images is a promising alternative which leverages a much broader source of supervision. We demonstrate that the simple pre-training task of predicting which caption goes with which image is an efficient and scalable way to learn SOTA image representations from scratch on a dataset of 400 million (image, text) pairs collected from the internet. After pre-training, natural language is used to reference learned visual concepts (or describe new ones) enabling zero-shot transfer of the model to downstream tasks. We study the performance of this approach by benchmarking on over 30 different existing computer vision datasets, spanning tasks such as OCR, action recognition in videos, geo-localization, and many types of fine-grained object classification. The model transfers non-trivially to most tasks and is often competitive with a fully supervised baseline without the need for any dataset specific training. For instance, we match the accuracy of the original ResNet-50 on ImageNet zero-shot without needing to use any of the 1.28 million training examples it was trained on. We release our code and pre-trained model weights at https://github.com/OpenAI/CLIP.
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.
Hateful meme detection is a new research area recently brought out that requires both visual, linguistic understanding of the meme and some background knowledge to performing well on the task. This technical report summarises the first place solution of the Hateful Meme Detection Challenge 2020, which extending state-of-the-art visual-linguistic transformers to tackle this problem. At the end of the report, we also point out the shortcomings and possible directions for improving the current methodology.
This work presents Vilio, an implementation of state-of-the-art visio-linguistic models and their application to the Hateful Memes Dataset. The implemented models have been fitted into a uniform code-base and altered to yield better performance. The goal of Vilio is to provide a user-friendly starting point for any visio-linguistic problem. An ensemble of 5 different V+L models implemented in Vilio achieves 2nd place in the Hateful Memes Challenge out of 3,300 participants. The code is available at https://github.com/Muennighoff/vilio.
This work proposes a new challenge set for multimodal classification, focusing on detecting hate speech in multimodal memes. It is constructed such that unimodal models struggle and only multimodal models can succeed: difficult examples ("benign confounders") are added to the dataset to make it hard to rely on unimodal signals. The task requires subtle reasoning, yet is straightforward to evaluate as a binary classification problem. We provide baseline performance numbers for unimodal models, as well as for multimodal models with various degrees of sophistication. We find that state-of-the-art methods perform poorly compared to humans (64.73% vs. 84.7% accuracy), illustrating the difficulty of the task and highlighting the challenge that this important problem poses to the community.
Image memes have become a widespread tool used by people for interacting and exchanging ideas over social media, blogs, and open messengers. This work proposes to treat automatic image meme generation as a translation process, and further present an end to end neural and probabilistic approach to generate an image-based meme for any given sentence using an encoder-decoder architecture. For a given input sentence, an image meme is generated by combining a meme template image and a text caption where the meme template image is selected from a set of popular candidates using a selection module, and the meme caption is generated by an encoder-decoder model. An encoder is used to map the selected meme template and the input sentence into a meme embedding and a decoder is used to decode the meme caption from the meme embedding. The generated natural language meme caption is conditioned on the input sentence and the selected meme template. The model learns the dependencies between the meme captions and the meme template images and generates new memes using the learned dependencies. The quality of the generated captions and the generated memes is evaluated through both automated and human evaluation. An experiment is designed to score how well the generated memes can represent the tweets from Twitter conversations. Experiments on Twitter data show the efficacy of the model in generating memes for sentences in online social interaction.