PowMix: A Versatile Regularizer for Multimodal Sentiment Analysis

Multimodal sentiment analysis (MSA) leverages heterogeneous data sources to interpret the complex nature of human sentiments. Despite significant progress in multimodal architecture design, the field lacks comprehensive regularization methods. This paper introduces PowMix, a versatile embedding space regularizer that builds upon the strengths of unimodal mixing-based regularization approaches and introduces novel algorithmic components that are specifically tailored to multimodal tasks. PowMix is integrated before the fusion stage of multimodal architectures and facilitates intra-modal mixing, such as mixing text with text, to act as a regularizer. PowMix consists of five components: 1) a varying number of generated mixed examples, 2) mixing factor reweighting, 3) anisotropic mixing, 4) dynamic mixing, and 5) cross-modal label mixing. Extensive experimentation across benchmark MSA datasets and a broad spectrum of diverse architectural designs demonstrate the efficacy of PowMix, as evidenced by consistent performance improvements over baselines and existing mixing methods. An in-depth ablation study highlights the critical contribution of each PowMix component and how they synergistically enhance performance. Furthermore, algorithmic analysis demonstrates how PowMix behaves in different scenarios, particularly comparing early versus late fusion architectures. Notably, PowMix enhances overall performance without sacrificing model robustness or magnifying text dominance. It also retains its strong performance in situations of limited data. Our findings position PowMix as a promising versatile regularization strategy for MSA. Code will be made available.

SeqAug: Sequential Feature Resampling as a modality agnostic augmentation method

Data augmentation is a prevalent technique for improving performance in various machine learning applications. We propose SeqAug, a modality-agnostic augmentation method that is tailored towards sequences of extracted features. The core idea of SeqAug is to augment the sequence by resampling from the underlying feature distribution. Resampling is performed by randomly selecting feature dimensions and permuting them along the temporal axis. Experiments on CMU-MOSEI verify that SeqAug is modality agnostic; it can be successfully applied to a single modality or multiple modalities. We further verify its compatibility with both recurrent and transformer architectures, and also demonstrate comparable to state-of-the-art results.

Alternating Objectives Generates Stronger PGD-Based Adversarial Attacks

Designing powerful adversarial attacks is of paramount importance for the evaluation of $\ell_p$-bounded adversarial defenses. Projected Gradient Descent (PGD) is one of the most effective and conceptually simple algorithms to generate such adversaries. The search space of PGD is dictated by the steepest ascent directions of an objective. Despite the plethora of objective function choices, there is no universally superior option and robustness overestimation may arise from ill-suited objective selection. Driven by this observation, we postulate that the combination of different objectives through a simple loss alternating scheme renders PGD more robust towards design choices. We experimentally verify this assertion on a synthetic-data example and by evaluating our proposed method across 25 different $\ell_{\infty}$-robust models and 3 datasets. The performance improvement is consistent, when compared to the single loss counterparts. In the CIFAR-10 dataset, our strongest adversarial attack outperforms all of the white-box components of AutoAttack (AA) ensemble, as well as the most powerful attacks existing on the literature, achieving state-of-the-art results in the computational budget of our study ($T=100$, no restarts).

A Multi-Task BERT Model for Schema-Guided Dialogue State Tracking

Task-oriented dialogue systems often employ a Dialogue State Tracker (DST) to successfully complete conversations. Recent state-of-the-art DST implementations rely on schemata of diverse services to improve model robustness and handle zero-shot generalization to new domains [1], however such methods [2, 3] typically require multiple large scale transformer models and long input sequences to perform well. We propose a single multi-task BERT-based model that jointly solves the three DST tasks of intent prediction, requested slot prediction and slot filling. Moreover, we propose an efficient and parsimonious encoding of the dialogue history and service schemata that is shown to further improve performance. Evaluation on the SGD dataset shows that our approach outperforms the baseline SGP-DST by a large margin and performs well compared to the state-of-the-art, while being significantly more computationally efficient. Extensive ablation studies are performed to examine the contributing factors to the success of our model.

Regotron: Regularizing the Tacotron2 architecture via monotonic alignment loss

Recent deep learning Text-to-Speech (TTS) systems have achieved impressive performance by generating speech close to human parity. However, they suffer from training stability issues as well as incorrect alignment of the intermediate acoustic representation with the input text sequence. In this work, we introduce Regotron, a regularized version of Tacotron2 which aims to alleviate the training issues and at the same time produce monotonic alignments. Our method augments the vanilla Tacotron2 objective function with an additional term, which penalizes non-monotonic alignments in the location-sensitive attention mechanism. By properly adjusting this regularization term we show that the loss curves become smoother, and at the same time Regotron consistently produces monotonic alignments in unseen examples even at an early stage (13\% of the total number of epochs) of its training process, whereas the fully converged Tacotron2 fails to do so. Moreover, our proposed regularization method has no additional computational overhead, while reducing common TTS mistakes and achieving slighlty improved speech naturalness according to subjective mean opinion scores (MOS) collected from 50 evaluators.

MMLatch: Bottom-up Top-down Fusion for Multimodal Sentiment Analysis

Current deep learning approaches for multimodal fusion rely on bottom-up fusion of high and mid-level latent modality representations (late/mid fusion) or low level sensory inputs (early fusion). Models of human perception highlight the importance of top-down fusion, where high-level representations affect the way sensory inputs are perceived, i.e. cognition affects perception. These top-down interactions are not captured in current deep learning models. In this work we propose a neural architecture that captures top-down cross-modal interactions, using a feedback mechanism in the forward pass during network training. The proposed mechanism extracts high-level representations for each modality and uses these representations to mask the sensory inputs, allowing the model to perform top-down feature masking. We apply the proposed model for multimodal sentiment recognition on CMU-MOSEI. Our method shows consistent improvements over the well established MulT and over our strong late fusion baseline, achieving state-of-the-art results.

AudioVisual Speech Synthesis: A brief literature review

This brief literature review studies the problem of audiovisual speech synthesis, which is the problem of generating an animated talking head given a text as input. Due to the high complexity of this problem, we approach it as the composition of two problems. Specifically, that of Text-to-Speech (TTS) synthesis as well as the voice-driven talking head animation. For TTS, we present models that are used to map text to intermediate acoustic representations, e.g. mel-spectrograms, as well as models that generate voice signals conditioned on these intermediate representations, i.e vocoders. For the talking-head animation problem, we categorize approaches based on whether they produce human faces or anthropomorphic figures. An attempt is also made to discuss the importance of the choice of facial models in the second case. Throughout the review, we briefly describe the most important work in audiovisual speech synthesis, trying to highlight the advantages and disadvantages of the various approaches.

End-to-end Generative Zero-shot Learning via Few-shot Learning

Contemporary state-of-the-art approaches to Zero-Shot Learning (ZSL) train generative nets to synthesize examples conditioned on the provided metadata. Thereafter, classifiers are trained on these synthetic data in a supervised manner. In this work, we introduce Z2FSL, an end-to-end generative ZSL framework that uses such an approach as a backbone and feeds its synthesized output to a Few-Shot Learning (FSL) algorithm. The two modules are trained jointly. Z2FSL solves the ZSL problem with a FSL algorithm, reducing, in effect, ZSL to FSL. A wide class of algorithms can be integrated within our framework. Our experimental results show consistent improvement over several baselines. The proposed method, evaluated across standard benchmarks, shows state-of-the-art or competitive performance in ZSL and Generalized ZSL tasks.