Facial expression recognition is a pivotal component in machine learning, facilitating various applications. However, convolutional neural networks (CNNs) are often plagued by catastrophic forgetting, impeding their adaptability. The proposed method, emotion-centered generative replay (ECgr), tackles this challenge by integrating synthetic images from generative adversarial networks. Moreover, ECgr incorporates a quality assurance algorithm to ensure the fidelity of generated images. This dual approach enables CNNs to retain past knowledge while learning new tasks, enhancing their performance in emotion recognition. The experimental results on four diverse facial expression datasets demonstrate that incorporating images generated by our pseudo-rehearsal method enhances training on the targeted dataset and the source dataset while making the CNN retain previously learned knowledge.
The study of human emotions, traditionally a cornerstone in fields like psychology and neuroscience, has been profoundly impacted by the advent of artificial intelligence (AI). Multiple channels, such as speech (voice) and facial expressions (image), are crucial in understanding human emotions. However, AI's journey in multimodal emotion recognition (MER) is marked by substantial technical challenges. One significant hurdle is how AI models manage the absence of a particular modality - a frequent occurrence in real-world situations. This study's central focus is assessing the performance and resilience of two strategies when confronted with the lack of one modality: a novel multimodal dynamic modality and view selection and a cross-attention mechanism. Results on the RECOLA dataset show that dynamic selection-based methods are a promising approach for MER. In the missing modalities scenarios, all dynamic selection-based methods outperformed the baseline. The study concludes by emphasizing the intricate interplay between audio and video modalities in emotion prediction, showcasing the adaptability of dynamic selection methods in handling missing modalities.
Systems and individuals produce data continuously. On the Internet, people share their knowledge, sentiments, and opinions, provide reviews about services and products, and so on. Automatically learning from these textual data can provide insights to organizations and institutions, thus preventing financial impacts, for example. To learn from textual data over time, the machine learning system must account for concept drift. Concept drift is a frequent phenomenon in real-world datasets and corresponds to changes in data distribution over time. For instance, a concept drift occurs when sentiments change or a word's meaning is adjusted over time. Although concept drift is frequent in real-world applications, benchmark datasets with labeled drifts are rare in the literature. To bridge this gap, this paper provides four textual drift generation methods to ease the production of datasets with labeled drifts. These methods were applied to Yelp and Airbnb datasets and tested using incremental classifiers respecting the stream mining paradigm to evaluate their ability to recover from the drifts. Results show that all methods have their performance degraded right after the drifts, and the incremental SVM is the fastest to run and recover the previous performance levels regarding accuracy and Macro F1-Score.
The proliferation of textual data on the Internet presents a unique opportunity for institutions and companies to monitor public opinion about their services and products. Given the rapid generation of such data, the text stream mining setting, which handles sequentially arriving, potentially infinite text streams, is often more suitable than traditional batch learning. While pre-trained language models are commonly employed for their high-quality text vectorization capabilities in streaming contexts, they face challenges adapting to concept drift - the phenomenon where the data distribution changes over time, adversely affecting model performance. Addressing the issue of concept drift, this study explores the efficacy of seven text sampling methods designed to selectively fine-tune language models, thereby mitigating performance degradation. We precisely assess the impact of these methods on fine-tuning the SBERT model using four different loss functions. Our evaluation, focused on Macro F1-score and elapsed time, employs two text stream datasets and an incremental SVM classifier to benchmark performance. Our findings indicate that Softmax loss and Batch All Triplets loss are particularly effective for text stream classification, demonstrating that larger sample sizes generally correlate with improved macro F1-scores. Notably, our proposed WordPieceToken ratio sampling method significantly enhances performance with the identified loss functions, surpassing baseline results.
Audiovisual emotion recognition (ER) in videos has immense potential over unimodal performance. It effectively leverages the inter- and intra-modal dependencies between visual and auditory modalities. This work proposes a novel audio-visual emotion recognition system utilizing a joint multimodal transformer architecture with key-based cross-attention. This framework aims to exploit the complementary nature of audio and visual cues (facial expressions and vocal patterns) in videos, leading to superior performance compared to solely relying on a single modality. The proposed model leverages separate backbones for capturing intra-modal temporal dependencies within each modality (audio and visual). Subsequently, a joint multimodal transformer architecture integrates the individual modality embeddings, enabling the model to effectively capture inter-modal (between audio and visual) and intra-modal (within each modality) relationships. Extensive evaluations on the challenging Affwild2 dataset demonstrate that the proposed model significantly outperforms baseline and state-of-the-art methods in ER tasks.
While state-of-the-art facial expression recognition (FER) classifiers achieve a high level of accuracy, they lack interpretability, an important aspect for end-users. To recognize basic facial expressions, experts resort to a codebook associating a set of spatial action units to a facial expression. In this paper, we follow the same expert footsteps, and propose a learning strategy that allows us to explicitly incorporate spatial action units (aus) cues into the classifier's training to build a deep interpretable model. In particular, using this aus codebook, input image expression label, and facial landmarks, a single action units heatmap is built to indicate the most discriminative regions of interest in the image w.r.t the facial expression. We leverage this valuable spatial cue to train a deep interpretable classifier for FER. This is achieved by constraining the spatial layer features of a classifier to be correlated with \aus map. Using a composite loss, the classifier is trained to correctly classify an image while yielding interpretable visual layer-wise attention correlated with aus maps, simulating the experts' decision process. This is achieved using only the image class expression as supervision and without any extra manual annotations. Moreover, our method is generic. It can be applied to any CNN- or transformer-based deep classifier without the need for architectural change or adding significant training time. Our extensive evaluation on two public benchmarks RAFDB, and AFFECTNET datasets shows that our proposed strategy can improve layer-wise interpretability without degrading classification performance. In addition, we explore a common type of interpretable classifiers that rely on Class-Activation Mapping methods (CAMs), and we show that our training technique improves the CAM interpretability.
Due to the advent and increase in the popularity of the Internet, people have been producing and disseminating textual data in several ways, such as reviews, social media posts, and news articles. As a result, numerous researchers have been working on discovering patterns in textual data, especially because social media posts function as social sensors, indicating peoples' opinions, interests, etc. However, most tasks regarding natural language processing are addressed using traditional machine learning methods and static datasets. This setting can lead to several problems, such as an outdated dataset, which may not correspond to reality, and an outdated model, which has its performance degrading over time. Concept drift is another aspect that emphasizes these issues, which corresponds to data distribution and pattern changes. In a text stream scenario, it is even more challenging due to its characteristics, such as the high speed and data arriving sequentially. In addition, models for this type of scenario must adhere to the constraints mentioned above while learning from the stream by storing texts for a limited time and consuming low memory. In this study, we performed a systematic literature review regarding concept drift adaptation in text stream scenarios. Considering well-defined criteria, we selected 40 papers to unravel aspects such as text drift categories, types of text drift detection, model update mechanism, the addressed stream mining tasks, types of text representations, and text representation update mechanism. In addition, we discussed drift visualization and simulation and listed real-world datasets used in the selected papers. Therefore, this paper comprehensively reviews the concept drift adaptation in text stream mining scenarios.
This paper presents a novel approach combining convolutional layers (CLs) and large-margin metric learning for training supervised models on small datasets for texture classification. The core of such an approach is a loss function that computes the distances between instances of interest and support vectors. The objective is to update the weights of CLs iteratively to learn a representation with a large margin between classes. Each iteration results in a large-margin discriminant model represented by support vectors based on such a representation. The advantage of the proposed approach w.r.t. convolutional neural networks (CNNs) is two-fold. First, it allows representation learning with a small amount of data due to the reduced number of parameters compared to an equivalent CNN. Second, it has a low training cost since the backpropagation considers only support vectors. The experimental results on texture and histopathologic image datasets have shown that the proposed approach achieves competitive accuracy with lower computational cost and faster convergence when compared to equivalent CNNs.
Data anonymization is often a task carried out by humans. Automating it would reduce the cost and time required to complete this task. This paper presents a pipeline to automate the anonymization of audio data in French. We propose a pipeline, which takes audio files with their transcriptions and removes the named entities (NEs) present in the audio. Our pipeline is made up of a forced aligner, which aligns words in an audio transcript with speech and a model that performs named entity recognition (NER). Then, the audio segments that correspond to NEs are substituted with silence to anonymize audio. We compared forced aligners and NER models to find the best ones for our scenario. We evaluated our pipeline on a small hand-annotated dataset, achieving an F1 score of 0.769. This result shows that automating this task is feasible.