The advancement of Large Language Models (LLMs), including GPT-4, provides exciting new opportunities for generative design. We investigate the application of this tool across the entire design and manufacturing workflow. Specifically, we scrutinize the utility of LLMs in tasks such as: converting a text-based prompt into a design specification, transforming a design into manufacturing instructions, producing a design space and design variations, computing the performance of a design, and searching for designs predicated on performance. Through a series of examples, we highlight both the benefits and the limitations of the current LLMs. By exposing these limitations, we aspire to catalyze the continued improvement and progression of these models.
Adriana Fernandez-Lopez, Honglie Chen, Pingchuan Ma et al.
Recent advances in deep neural networks have achieved unprecedented success in visual speech recognition. However, there remains substantial disparity between current methods and their deployment in resource-constrained devices. In this work, we explore different magnitude-based pruning techniques to generate a lightweight model that achieves higher performance than its dense model equivalent, especially under the presence of visual noise. Our sparse models achieve state-of-the-art results at 10% sparsity on the LRS3 dataset and outperform the dense equivalent up to 70% sparsity. We evaluate our 50% sparse model on 7 different visual noise types and achieve an overall absolute improvement of more than 2% WER compared to the dense equivalent. Our results confirm that sparse networks are more resistant to noise than dense networks.
Yunsheng Tian, Karl D. D. Willis, Bassel Al Omari et al.
The automated assembly of complex products requires a system that can automatically plan a physically feasible sequence of actions for assembling many parts together. In this paper, we present ASAP, a physics-based planning approach for automatically generating such a sequence for general-shaped assemblies. ASAP accounts for gravity to design a sequence where each sub-assembly is physically stable with a limited number of parts being held and a support surface. We apply efficient tree search algorithms to reduce the combinatorial complexity of determining such an assembly sequence. The search can be guided by either geometric heuristics or graph neural networks trained on data with simulation labels. Finally, we show the superior performance of ASAP at generating physically realistic assembly sequence plans on a large dataset of hundreds of complex product assemblies. We further demonstrate the applicability of ASAP on both simulation and real-world robotic setups. Project website: asap.csail.mit.edu
A major challenge of AI + Science lies in their inherent incompatibility: today's AI is primarily based on connectionism, while science depends on symbolism. To bridge the two worlds, we propose a framework to seamlessly synergize Kolmogorov-Arnold Networks (KANs) and science. The framework highlights KANs' usage for three aspects of scientific discovery: identifying relevant features, revealing modular structures, and discovering symbolic formulas. The synergy is bidirectional: science to KAN (incorporating scientific knowledge into KANs), and KAN to science (extracting scientific insights from KANs). We highlight major new functionalities in the pykan package: (1) MultKAN: KANs with multiplication nodes. (2) kanpiler: a KAN compiler that compiles symbolic formulas into KANs. (3) tree converter: convert KANs (or any neural networks) to tree graphs. Based on these tools, we demonstrate KANs' capability to discover various types of physical laws, including conserved quantities, Lagrangians, symmetries, and constitutive laws.
Understanding causal relations is vital in scientific discovery. The process of causal structure learning involves identifying causal graphs from observational data to understand such relations. Usually, a central server performs this task, but sharing data with the server poses privacy risks. Federated learning can solve this problem, but existing solutions for federated causal structure learning make unrealistic assumptions about data and lack convergence guarantees. FedC2SL is a federated constraint-based causal structure learning scheme that learns causal graphs using a federated conditional independence test, which examines conditional independence between two variables under a condition set without collecting raw data from clients. FedC2SL requires weaker and more realistic assumptions about data and offers stronger resistance to data variability among clients. FedPC and FedFCI are the two variants of FedC2SL for causal structure learning in causal sufficiency and causal insufficiency, respectively. The study evaluates FedC2SL using both synthetic datasets and real-world data against existing solutions and finds it demonstrates encouraging performance and strong resilience to data heterogeneity among clients.
Human motion synthesis is a fundamental task in computer animation. Recent methods based on diffusion models or GPT structure demonstrate commendable performance but exhibit drawbacks in terms of slow sampling speeds and error accumulation. In this paper, we propose \emph{Motion Flow Matching}, a novel generative model designed for human motion generation featuring efficient sampling and effectiveness in motion editing applications. Our method reduces the sampling complexity from thousand steps in previous diffusion models to just ten steps, while achieving comparable performance in text-to-motion and action-to-motion generation benchmarks. Noticeably, our approach establishes a new state-of-the-art Fréchet Inception Distance on the KIT-ML dataset. What is more, we tailor a straightforward motion editing paradigm named \emph{sampling trajectory rewriting} leveraging the ODE-style generative models and apply it to various editing scenarios including motion prediction, motion in-between prediction, motion interpolation, and upper-body editing. Our code will be released.
Recently, differentiable causal discovery has emerged as a promising approach to improve the accuracy and efficiency of existing methods. However, when applied to high-dimensional data or data with latent confounders, these methods, often based on off-the-shelf continuous optimization algorithms, struggle with the vast search space, the complexity of the objective function, and the nontrivial nature of graph-theoretical constraints. As a result, there has been a surge of interest in leveraging super-structures to guide the optimization process. Nonetheless, learning an appropriate super-structure at the right level of granularity, and doing so efficiently across various settings, presents significant challenges. In this paper, we propose ALVGL, a novel and general enhancement to the differentiable causal discovery pipeline. ALVGL employs a sparse and low-rank decomposition to learn the precision matrix of the data. We design an ADMM procedure to optimize this decomposition, identifying components in the precision matrix that are most relevant to the underlying causal structure. These components are then combined to construct a super-structure that is provably a superset of the true causal graph. This super-structure is used to initialize a standard differentiable causal discovery method with a more focused search space, thereby improving both optimization efficiency and accuracy. We demonstrate the versatility of ALVGL by instantiating it across a range of structural causal models, including both Gaussian and non-Gaussian settings, with and without unmeasured confounders. Extensive experiments on synthetic and real-world datasets show that ALVGL not only achieves state-of-the-art accuracy but also significantly improves optimization efficiency, making it a reliable and effective solution for differentiable causal discovery.
Inverse design has emerged as a transformative approach for photonic device optimization, enabling the exploration of high-dimensional, non-intuitive design spaces to create ultra-compact devices and advance photonic integrated circuits (PICs) in computing and interconnects. However, practical challenges, such as suboptimal device performance, limited manufacturability, high sensitivity to variations, computational inefficiency, and lack of interpretability, have hindered its adoption in commercial hardware. Recent advancements in AI-assisted photonic simulation and design offer transformative potential, accelerating simulations and design generation by orders of magnitude over traditional numerical methods. Despite these breakthroughs, the lack of an open-source, standardized infrastructure and evaluation benchmark limits accessibility and cross-disciplinary collaboration. To address this, we introduce MAPS, a multi-fidelity AI-augmented photonic simulation and inverse design infrastructure designed to bridge this gap. MAPS features three synergistic components: (1) MAPS-Data: A dataset acquisition framework for generating multi-fidelity, richly labeled devices, providing high-quality data for AI-for-optics research. (2) MAPS-Train: A flexible AI-for-photonics training framework offering a hierarchical data loading pipeline, customizable model construction, support for data- and physics-driven losses, and comprehensive evaluations. (3) MAPS-InvDes: An advanced adjoint inverse design toolkit that abstracts complex physics but exposes flexible optimization steps, integrates pre-trained AI models, and incorporates fabrication variation models. This infrastructure MAPS provides a unified, open-source platform for developing, benchmarking, and advancing AI-assisted photonic design workflows, accelerating innovation in photonic hardware optimization and scientific machine learning.
DONNs leverage light propagation for efficient analog AI and signal processing. Advances in nanophotonic fabrication and metasurface-based wavefront engineering have opened new pathways to realize high-capacity DONNs across various spectral regimes. Training such DONN systems to determine the metasurface structures remains challenging. Heuristic methods are fast but oversimplify metasurfaces modulation, often resulting in physically unrealizable designs and significant performance degradation. Simulation-in-the-loop optimizes implementable metasurfaces via adjoint methods, but is computationally prohibitive and unscalable. To address these limitations, we propose SP2RINT, a spatially decoupled, progressive training framework that formulates DONN training as a PDE-constrained learning problem. Metasurface responses are first relaxed into freely trainable transfer matrices with a banded structure. We then progressively enforce physical constraints by alternating between transfer matrix training and adjoint-based inverse design, avoiding per-iteration PDE solves while ensuring final physical realizability. To further reduce runtime, we introduce a physics-inspired, spatially decoupled inverse design strategy based on the natural locality of field interactions. This approach partitions the metasurface into independently solvable patches, enabling scalable and parallel inverse design with system-level calibration. Evaluated across diverse DONN training tasks, SP2RINT achieves digital-comparable accuracy while being 1825 times faster than simulation-in-the-loop approaches. By bridging the gap between abstract DONN models and implementable photonic hardware, SP2RINT enables scalable, high-performance training of physically realizable meta-optical neural systems. Our code is available at https://github.com/ScopeX-ASU/SP2RINT
Diffusion Models are popular generative modeling methods in various vision tasks, attracting significant attention. They can be considered a unique instance of self-supervised learning methods due to their independence from label annotation. This survey explores the interplay between diffusion models and representation learning. It provides an overview of diffusion models' essential aspects, including mathematical foundations, popular denoising network architectures, and guidance methods. Various approaches related to diffusion models and representation learning are detailed. These include frameworks that leverage representations learned from pre-trained diffusion models for subsequent recognition tasks and methods that utilize advancements in representation and self-supervised learning to enhance diffusion models. This survey aims to offer a comprehensive overview of the taxonomy between diffusion models and representation learning, identifying key areas of existing concerns and potential exploration. Github link: https://github.com/dongzhuoyao/Diffusion-Representation-Learning-Survey-Taxonomy
The finite-difference time-domain (FDTD) method, which is important in photonic hardware design flow, is widely adopted to solve time-domain Maxwell equations. However, FDTD is known for its prohibitive runtime cost, taking minutes to hours to simulate a single device. Recently, AI has been applied to realize orders-of-magnitude speedup in partial differential equation (PDE) solving. However, AI-based FDTD solvers for photonic devices have not been clearly formulated. Directly applying off-the-shelf models to predict the optical field dynamics shows unsatisfying fidelity and efficiency since the model primitives are agnostic to the unique physical properties of Maxwell equations and lack algorithmic customization. In this work, we thoroughly investigate the synergy between neural operator designs and the physical property of Maxwell equations and introduce a physics-inspired AI-based FDTD prediction framework PIC2O-Sim which features a causality-aware dynamic convolutional neural operator as its backbone model that honors the space-time causality constraints via careful receptive field configuration and explicitly captures the permittivity-dependent light propagation behavior via an efficient dynamic convolution operator. Meanwhile, we explore the trade-offs among prediction scalability, fidelity, and efficiency via a multi-stage partitioned time-bundling technique in autoregressive prediction. Multiple key techniques have been introduced to mitigate iterative error accumulation while maintaining efficiency advantages during autoregressive field prediction. Extensive evaluations on three challenging photonic device simulation tasks have shown the superiority of our PIC2O-Sim method, showing 51.2% lower roll-out prediction error, 23.5 times fewer parameters than state-of-the-art neural operators, providing 300-600x higher simulation speed than an open-source FDTD numerical solver.
Vincent Tao Hu, Stefan Andreas Baumann, Ming Gui et al.
The diffusion model has long been plagued by scalability and quadratic complexity issues, especially within transformer-based structures. In this study, we aim to leverage the long sequence modeling capability of a State-Space Model called Mamba to extend its applicability to visual data generation. Firstly, we identify a critical oversight in most current Mamba-based vision methods, namely the lack of consideration for spatial continuity in the scan scheme of Mamba. Secondly, building upon this insight, we introduce a simple, plug-and-play, zero-parameter method named Zigzag Mamba, which outperforms Mamba-based baselines and demonstrates improved speed and memory utilization compared to transformer-based baselines. Lastly, we integrate Zigzag Mamba with the Stochastic Interpolant framework to investigate the scalability of the model on large-resolution visual datasets, such as FacesHQ $1024\times 1024$ and UCF101, MultiModal-CelebA-HQ, and MS COCO $256\times 256$ . Code will be released at https://taohu.me/zigma/
Ming Gui, Johannes Schusterbauer, Ulrich Prestel et al.
Current discriminative depth estimation methods often produce blurry artifacts, while generative approaches suffer from slow sampling due to curvatures in the noise-to-depth transport. Our method addresses these challenges by framing depth estimation as a direct transport between image and depth distributions. We are the first to explore flow matching in this field, and we demonstrate that its interpolation trajectories enhance both training and sampling efficiency while preserving high performance. While generative models typically require extensive training data, we mitigate this dependency by integrating external knowledge from a pre-trained image diffusion model, enabling effective transfer even across differing objectives. To further boost our model performance, we employ synthetic data and utilize image-depth pairs generated by a discriminative model on an in-the-wild image dataset. As a generative model, our model can reliably estimate depth confidence, which provides an additional advantage. Our approach achieves competitive zero-shot performance on standard benchmarks of complex natural scenes while improving sampling efficiency and only requiring minimal synthetic data for training.
Johannes Schusterbauer, Ming Gui, Pingchuan Ma et al.
Visual synthesis has recently seen significant leaps in performance, largely due to breakthroughs in generative models. Diffusion models have been a key enabler, as they excel in image diversity. However, this comes at the cost of slow training and synthesis, which is only partially alleviated by latent diffusion. To this end, flow matching is an appealing approach due to its complementary characteristics of faster training and inference but less diverse synthesis. We demonstrate that introducing flow matching between a frozen diffusion model and a convolutional decoder enables high-resolution image synthesis at reduced computational cost and model size. A small diffusion model can then effectively provide the necessary visual diversity, while flow matching efficiently enhances resolution and detail by mapping the small to a high-dimensional latent space. These latents are then projected to high-resolution images by the subsequent convolutional decoder of the latent diffusion approach. Combining the diversity of diffusion models, the efficiency of flow matching, and the effectiveness of convolutional decoders, state-of-the-art high-resolution image synthesis is achieved at $1024^2$ pixels with minimal computational cost. Further scaling up our method we can reach resolutions up to $2048^2$ pixels. Importantly, our approach is orthogonal to recent approximation and speed-up strategies for the underlying model, making it easily integrable into the various diffusion model frameworks.
Natural language often struggles to accurately associate positional and attribute information with multiple instances, which limits current text-based visual generation models to simpler compositions featuring only a few dominant instances. To address this limitation, this work enhances diffusion models by introducing regional instance control, where each instance is governed by a bounding box paired with a free-form caption. Previous methods in this area typically rely on implicit position encoding or explicit attention masks to separate regions of interest (ROIs), resulting in either inaccurate coordinate injection or large computational overhead. Inspired by ROI-Align in object detection, we introduce a complementary operation called ROI-Unpool. Together, ROI-Align and ROI-Unpool enable explicit, efficient, and accurate ROI manipulation on high-resolution feature maps for visual generation. Building on ROI-Unpool, we propose ROICtrl, an adapter for pretrained diffusion models that enables precise regional instance control. ROICtrl is compatible with community-finetuned diffusion models, as well as with existing spatial-based add-ons (\eg, ControlNet, T2I-Adapter) and embedding-based add-ons (\eg, IP-Adapter, ED-LoRA), extending their applications to multi-instance generation. Experiments show that ROICtrl achieves superior performance in regional instance control while significantly reducing computational costs.
Recent years have witnessed the rapid development of large language models (LLMs) in various domains. To better serve the large number of Chinese users, many commercial vendors in China have adopted localization strategies, training and providing local LLMs specifically customized for Chinese users. Furthermore, looking ahead, one of the key future applications of LLMs will be practical deployment in industrial production by enterprises and users in those sectors. However, the accuracy and robustness of LLMs in industrial scenarios have not been well studied. In this paper, we present a comprehensive empirical study on the accuracy and robustness of LLMs in the context of the Chinese industrial production area. We manually collected 1,200 domain-specific problems from 8 different industrial sectors to evaluate LLM accuracy. Furthermore, we designed a metamorphic testing framework containing four industrial-specific stability categories with eight abilities, totaling 13,631 questions with variants to evaluate LLM robustness. In total, we evaluated 9 different LLMs developed by Chinese vendors, as well as four different LLMs developed by global vendors. Our major findings include: (1) Current LLMs exhibit low accuracy in Chinese industrial contexts, with all LLMs scoring less than 0.6. (2) The robustness scores vary across industrial sectors, and local LLMs overall perform worse than global ones. (3) LLM robustness differs significantly across abilities. Global LLMs are more robust under logical-related variants, while advanced local LLMs perform better on problems related to understanding Chinese industrial terminology. Our study results provide valuable guidance for understanding and promoting the industrial domain capabilities of LLMs from both development and industrial enterprise perspectives. The results further motivate possible research directions and tooling support.
Pingchuan Ma, Lennart Rietdorf, Dmytro Kotovenko et al.
Accurately describing images with text is a foundation of explainable AI. Vision-Language Models (VLMs) like CLIP have recently addressed this by aligning images and texts in a shared embedding space, expressing semantic similarities between vision and language embeddings. VLM classification can be improved with descriptions generated by Large Language Models (LLMs). However, it is difficult to determine the contribution of actual description semantics, as the performance gain may also stem from a semantic-agnostic ensembling effect, where multiple modified text prompts act as a noisy test-time augmentation for the original one. We propose an alternative evaluation scenario to decide if a performance boost of LLM-generated descriptions is caused by such a noise augmentation effect or rather by genuine description semantics. The proposed scenario avoids noisy test-time augmentation and ensures that genuine, distinctive descriptions cause the performance boost. Furthermore, we propose a training-free method for selecting discriminative descriptions that work independently of classname-ensembling effects. Our approach identifies descriptions that effectively differentiate classes within a local CLIP label neighborhood, improving classification accuracy across seven datasets. Additionally, we provide insights into the explainability of description-based image classification with VLMs.
This paper explores multi-modal controllable Text-to-Speech Synthesis (TTS) where the voice can be generated from face image, and the characteristics of output speech (e.g., pace, noise level, distance, tone, place) can be controllable with natural text description. Specifically, we aim to mitigate the following three challenges in face-driven TTS systems. 1) To overcome the limited audio quality of audio-visual speech corpora, we propose a training method that additionally utilizes high-quality audio-only speech corpora. 2) To generate voices not only from real human faces but also from artistic portraits, we propose augmenting the input face image with stylization. 3) To consider one-to-many possibilities in face-to-voice mapping and ensure consistent voice generation at the same time, we propose to first employ sampling-based decoding and then use prompting with generated speech samples. Experimental results validate the proposed model's effectiveness in face-driven voice synthesis.
Adriana Fernandez-Lopez, Honglie Chen, Pingchuan Ma et al.
Pre-trained models have been a foundational approach in speech recognition, albeit with associated additional costs. In this study, we propose a regularization technique that facilitates the training of visual and audio-visual speech recognition models (VSR and AVSR) from scratch. This approach, abbreviated as \textbf{MSRS} (Multimodal Speech Recognition from Scratch), introduces a sparse regularization that rapidly learns sparse structures within the dense model at the very beginning of training, which receives healthier gradient flow than the dense equivalent. Once the sparse mask stabilizes, our method allows transitioning to a dense model or keeping a sparse model by updating non-zero values. MSRS achieves competitive results in VSR and AVSR with 21.1% and 0.9% WER on the LRS3 benchmark, while reducing training time by at least 2x. We explore other sparse approaches and show that only MSRS enables training from scratch by implicitly masking the weights affected by vanishing gradients.
Differentiable causal discovery has made significant advancements in the learning of directed acyclic graphs. However, its application to real-world datasets remains restricted due to the ubiquity of latent confounders and the requirement to learn maximal ancestral graphs (MAGs). To date, existing differentiable MAG learning algorithms have been limited to small datasets and failed to scale to larger ones (e.g., with more than 50 variables). The key insight in this paper is that the causal skeleton, which is the undirected version of the causal graph, has potential for improving accuracy and reducing the search space of the optimization procedure, thereby enhancing the performance of differentiable causal discovery. Therefore, we seek to address a two-fold challenge to harness the potential of the causal skeleton for differentiable causal discovery in the presence of latent confounders: (1) scalable and accurate estimation of skeleton and (2) universal integration of skeleton estimation with differentiable causal discovery. To this end, we propose SPOT (Skeleton Posterior-guided OpTimization), a two-phase framework that harnesses skeleton posterior for differentiable causal discovery in the presence of latent confounders. On the contrary to a ``point-estimation'', SPOT seeks to estimate the posterior distribution of skeletons given the dataset. It first formulates the posterior inference as an instance of amortized inference problem and concretizes it with a supervised causal learning (SCL)-enabled solution to estimate the skeleton posterior. To incorporate the skeleton posterior with differentiable causal discovery, SPOT then features a skeleton posterior-guided stochastic optimization procedure to guide the optimization of MAGs. [abridged due to length limit]
Artsiom Sanakoyeu, Pingchuan Ma, Vadim Tschernezki et al.
Deep metric learning (DML) is a cornerstone of many computer vision applications. It aims at learning a mapping from the input domain to an embedding space, where semantically similar objects are located nearby and dissimilar objects far from another. The target similarity on the training data is defined by user in form of ground-truth class labels. However, while the embedding space learns to mimic the user-provided similarity on the training data, it should also generalize to novel categories not seen during training. Besides user-provided groundtruth training labels, a lot of additional visual factors (such as viewpoint changes or shape peculiarities) exist and imply different notions of similarity between objects, affecting the generalization on the images unseen during training. However, existing approaches usually directly learn a single embedding space on all available training data, struggling to encode all different types of relationships, and do not generalize well. We propose to build a more expressive representation by jointly splitting the embedding space and the data hierarchically into smaller sub-parts. We successively focus on smaller subsets of the training data, reducing its variance and learning a different embedding subspace for each data subset. Moreover, the subspaces are learned jointly to cover not only the intricacies, but the breadth of the data as well. Only after that, we build the final embedding from the subspaces in the conquering stage. The proposed algorithm acts as a transparent wrapper that can be placed around arbitrary existing DML methods. Our approach significantly improves upon the state-of-the-art on image retrieval, clustering, and re-identification tasks evaluated using CUB200-2011, CARS196, Stanford Online Products, In-shop Clothes, and PKU VehicleID datasets.
Pingchuan Ma, Rodrigo Mira, Stavros Petridis et al.
The large amount of audiovisual content being shared online today has drawn substantial attention to the prospect of audiovisual self-supervised learning. Recent works have focused on each of these modalities separately, while others have attempted to model both simultaneously in a cross-modal fashion. However, comparatively little attention has been given to leveraging one modality as a training objective to learn from the other. In this work, we propose Learning visual speech Representations from Audio via self-supervision (LiRA). Specifically, we train a ResNet+Conformer model to predict acoustic features from unlabelled visual speech. We find that this pre-trained model can be leveraged towards word-level and sentence-level lip-reading through feature extraction and fine-tuning experiments. We show that our approach significantly outperforms other self-supervised methods on the Lip Reading in the Wild (LRW) dataset and achieves state-of-the-art performance on Lip Reading Sentences 2 (LRS2) using only a fraction of the total labelled data.
Rodrigo Mira, Konstantinos Vougioukas, Pingchuan Ma et al.
Video-to-speech is the process of reconstructing the audio speech from a video of a spoken utterance. Previous approaches to this task have relied on a two-step process where an intermediate representation is inferred from the video, and is then decoded into waveform audio using a vocoder or a waveform reconstruction algorithm. In this work, we propose a new end-to-end video-to-speech model based on Generative Adversarial Networks (GANs) which translates spoken video to waveform end-to-end without using any intermediate representation or separate waveform synthesis algorithm. Our model consists of an encoder-decoder architecture that receives raw video as input and generates speech, which is then fed to a waveform critic and a power critic. The use of an adversarial loss based on these two critics enables the direct synthesis of raw audio waveform and ensures its realism. In addition, the use of our three comparative losses helps establish direct correspondence between the generated audio and the input video. We show that this model is able to reconstruct speech with remarkable realism for constrained datasets such as GRID, and that it is the first end-to-end model to produce intelligible speech for LRW (Lip Reading in the Wild), featuring hundreds of speakers recorded entirely `in the wild'. We evaluate the generated samples in two different scenarios -- seen and unseen speakers -- using four objective metrics which measure the quality and intelligibility of artificial speech. We demonstrate that the proposed approach outperforms all previous works in most metrics on GRID and LRW.
In this work, we present a hybrid CTC/Attention model based on a ResNet-18 and Convolution-augmented transformer (Conformer), that can be trained in an end-to-end manner. In particular, the audio and visual encoders learn to extract features directly from raw pixels and audio waveforms, respectively, which are then fed to conformers and then fusion takes place via a Multi-Layer Perceptron (MLP). The model learns to recognise characters using a combination of CTC and an attention mechanism. We show that end-to-end training, instead of using pre-computed visual features which is common in the literature, the use of a conformer, instead of a recurrent network, and the use of a transformer-based language model, significantly improve the performance of our model. We present results on the largest publicly available datasets for sentence-level speech recognition, Lip Reading Sentences 2 (LRS2) and Lip Reading Sentences 3 (LRS3), respectively. The results show that our proposed models raise the state-of-the-art performance by a large margin in audio-only, visual-only, and audio-visual experiments.
In this work, we present the Densely Connected Temporal Convolutional Network (DC-TCN) for lip-reading of isolated words. Although Temporal Convolutional Networks (TCN) have recently demonstrated great potential in many vision tasks, its receptive fields are not dense enough to model the complex temporal dynamics in lip-reading scenarios. To address this problem, we introduce dense connections into the network to capture more robust temporal features. Moreover, our approach utilises the Squeeze-and-Excitation block, a light-weight attention mechanism, to further enhance the model's classification power. Without bells and whistles, our DC-TCN method has achieved 88.36% accuracy on the Lip Reading in the Wild (LRW) dataset and 43.65% on the LRW-1000 dataset, which has surpassed all the baseline methods and is the new state-of-the-art on both datasets.
Pingchuan Ma, Brais Martinez, Stavros Petridis et al.
Lipreading has witnessed a lot of progress due to the resurgence of neural networks. Recent works have placed emphasis on aspects such as improving performance by finding the optimal architecture or improving generalization. However, there is still a significant gap between the current methodologies and the requirements for an effective deployment of lipreading in practical scenarios. In this work, we propose a series of innovations that significantly bridge that gap: first, we raise the state-of-the-art performance by a wide margin on LRW and LRW-1000 to 88.5% and 46.6%, respectively using self-distillation. Secondly, we propose a series of architectural changes, including a novel Depthwise Separable Temporal Convolutional Network (DS-TCN) head, that slashes the computational cost to a fraction of the (already quite efficient) original model. Thirdly, we show that knowledge distillation is a very effective tool for recovering performance of the lightweight models. This results in a range of models with different accuracy-efficiency trade-offs. However, our most promising lightweight models are on par with the current state-of-the-art while showing a reduction of 8.2x and 3.9x in terms of computational cost and number of parameters, respectively, which we hope will enable the deployment of lipreading models in practical applications.
Tasks in multi-task learning often correlate, conflict, or even compete with each other. As a result, a single solution that is optimal for all tasks rarely exists. Recent papers introduced the concept of Pareto optimality to this field and directly cast multi-task learning as multi-objective optimization problems, but solutions returned by existing methods are typically finite, sparse, and discrete. We present a novel, efficient method that generates locally continuous Pareto sets and Pareto fronts, which opens up the possibility of continuous analysis of Pareto optimal solutions in machine learning problems. We scale up theoretical results in multi-objective optimization to modern machine learning problems by proposing a sample-based sparse linear system, for which standard Hessian-free solvers in machine learning can be applied. We compare our method to the state-of-the-art algorithms and demonstrate its usage of analyzing local Pareto sets on various multi-task classification and regression problems. The experimental results confirm that our algorithm reveals the primary directions in local Pareto sets for trade-off balancing, finds more solutions with different trade-offs efficiently, and scales well to tasks with millions of parameters.
Brais Martinez, Pingchuan Ma, Stavros Petridis et al.
Lip-reading has attracted a lot of research attention lately thanks to advances in deep learning. The current state-of-the-art model for recognition of isolated words in-the-wild consists of a residual network and Bidirectional Gated Recurrent Unit (BGRU) layers. In this work, we address the limitations of this model and we propose changes which further improve its performance. Firstly, the BGRU layers are replaced with Temporal Convolutional Networks (TCN). Secondly, we greatly simplify the training procedure, which allows us to train the model in one single stage. Thirdly, we show that the current state-of-the-art methodology produces models that do not generalize well to variations on the sequence length, and we addresses this issue by proposing a variable-length augmentation. We present results on the largest publicly-available datasets for isolated word recognition in English and Mandarin, LRW and LRW1000, respectively. Our proposed model results in an absolute improvement of 1.2% and 3.2%, respectively, in these datasets which is the new state-of-the-art performance.
Abhinav Shukla, Konstantinos Vougioukas, Pingchuan Ma et al.
Self supervised representation learning has recently attracted a lot of research interest for both the audio and visual modalities. However, most works typically focus on a particular modality or feature alone and there has been very limited work that studies the interaction between the two modalities for learning self supervised representations. We propose a framework for learning audio representations guided by the visual modality in the context of audiovisual speech. We employ a generative audio-to-video training scheme in which we animate a still image corresponding to a given audio clip and optimize the generated video to be as close as possible to the real video of the speech segment. Through this process, the audio encoder network learns useful speech representations that we evaluate on emotion recognition and speech recognition. We achieve state of the art results for emotion recognition and competitive results for speech recognition. This demonstrates the potential of visual supervision for learning audio representations as a novel way for self-supervised learning which has not been explored in the past. The proposed unsupervised audio features can leverage a virtually unlimited amount of training data of unlabelled audiovisual speech and have a large number of potentially promising applications.
Adversarial attacks pose a threat to deep learning models. However, research on adversarial detection methods, especially in the multi-modal domain, is very limited. In this work, we propose an efficient and straightforward detection method based on the temporal correlation between audio and video streams. The main idea is that the correlation between audio and video in adversarial examples will be lower than benign examples due to added adversarial noise. We use the synchronisation confidence score as a proxy for audiovisual correlation and based on it we can detect adversarial attacks. To the best of our knowledge, this is the first work on detection of adversarial attacks on audiovisual speech recognition models. We apply recent adversarial attacks on two audiovisual speech recognition models trained on the GRID and LRW datasets. The experimental results demonstrate that the proposed approach is an effective way for detecting such attacks.
3D CNN shows its strong ability in learning spatiotemporal representation in recent video recognition tasks. However, inflating 2D convolution to 3D inevitably introduces additional computational costs, making it cumbersome in practical deployment. We consider whether there is a way to equip the conventional 2D convolution with temporal vision no requiring expanding its kernel. To this end, we propose the video shuffle, a parameter-free plug-in component that efficiently reallocates the inputs of 2D convolution so that its receptive field can be extended to the temporal dimension. In practical, video shuffle firstly divides each frame feature into multiple groups and then aggregate the grouped features via temporal shuffle operation. This allows the following 2D convolution aggregate the global spatiotemporal features. The proposed video shuffle can be flexibly inserted into popular 2D CNNs, forming the Video Shuffle Networks (VSN). With a simple yet efficient implementation, VSN performs surprisingly well on temporal modeling benchmarks. In experiments, VSN not only gains non-trivial improvements on Kinetics and Moments in Time, but also achieves state-of-the-art performance on Something-Something-V1, Something-Something-V2 datasets.
Shiyang Cheng, Pingchuan Ma, Georgios Tzimiropoulos et al.
Lip-reading models have been significantly improved recently thanks to powerful deep learning architectures. However, most works focused on frontal or near frontal views of the mouth. As a consequence, lip-reading performance seriously deteriorates in non-frontal mouth views. In this work, we present a framework for training pose-invariant lip-reading models on synthetic data instead of collecting and annotating non-frontal data which is costly and tedious. The proposed model significantly outperforms previous approaches on non-frontal views while retaining the superior performance on frontal and near frontal mouth views. Specifically, we propose to use a 3D Morphable Model (3DMM) to augment LRW, an existing large-scale but mostly frontal dataset, by generating synthetic facial data in arbitrary poses. The newly derived dataset, is used to train a state-of-the-art neural network for lip-reading. We conducted a cross-database experiment for isolated word recognition on the LRS2 dataset, and reported an absolute improvement of 2.55%. The benefit of the proposed approach becomes clearer in extreme poses where an absolute improvement of up to 20.64% over the baseline is achieved.
Konstantinos Vougioukas, Pingchuan Ma, Stavros Petridis et al.
Speech is a means of communication which relies on both audio and visual information. The absence of one modality can often lead to confusion or misinterpretation of information. In this paper we present an end-to-end temporal model capable of directly synthesising audio from silent video, without needing to transform to-and-from intermediate features. Our proposed approach, based on GANs is capable of producing natural sounding, intelligible speech which is synchronised with the video. The performance of our model is evaluated on the GRID dataset for both speaker dependent and speaker independent scenarios. To the best of our knowledge this is the first method that maps video directly to raw audio and the first to produce intelligible speech when tested on previously unseen speakers. We evaluate the synthesised audio not only based on the sound quality but also on the accuracy of the spoken words.
Several audio-visual speech recognition models have been recently proposed which aim to improve the robustness over audio-only models in the presence of noise. However, almost all of them ignore the impact of the Lombard effect, i.e., the change in speaking style in noisy environments which aims to make speech more intelligible and affects both the acoustic characteristics of speech and the lip movements. In this paper, we investigate the impact of the Lombard effect in audio-visual speech recognition. To the best of our knowledge, this is the first work which does so using end-to-end deep architectures and presents results on unseen speakers. Our results show that properly modelling Lombard speech is always beneficial. Even if a relatively small amount of Lombard speech is added to the training set then the performance in a real scenario, where noisy Lombard speech is present, can be significantly improved. We also show that the standard approach followed in the literature, where a model is trained and tested on noisy plain speech, provides a correct estimate of the video-only performance and slightly underestimates the audio-visual performance. In case of audio-only approaches, performance is overestimated for SNRs higher than -3dB and underestimated for lower SNRs.
Stavros Petridis, Yujiang Wang, Pingchuan Ma et al.
Visual speech recognition models traditionally consist of two stages, feature extraction and classification. Several deep learning approaches have been recently presented aiming to replace the feature extraction stage by automatically extracting features from mouth images. However, research on joint learning of features and classification remains limited. In addition, most of the existing methods require large amounts of data in order to achieve state-of-the-art performance, otherwise they under-perform. In this work, we present an end-to-end visual speech recognition system based on fully-connected layers and Long-Short Memory (LSTM) networks which is suitable for small-scale datasets. The model consists of two streams which extract features directly from the mouth and difference images, respectively. The temporal dynamics in each stream are modelled by a Bidirectional LSTM (BLSTM) and the fusion of the two streams takes place via another BLSTM. An absolute improvement of 0.6%, 3.4%, 3.9%, 11.4% over the state-of-the-art is reported on the OuluVS2, CUAVE, AVLetters and AVLetters2 databases, respectively.
Stavros Petridis, Themos Stafylakis, Pingchuan Ma et al.
Recent works in speech recognition rely either on connectionist temporal classification (CTC) or sequence-to-sequence models for character-level recognition. CTC assumes conditional independence of individual characters, whereas attention-based models can provide nonsequential alignments. Therefore, we could use a CTC loss in combination with an attention-based model in order to force monotonic alignments and at the same time get rid of the conditional independence assumption. In this paper, we use the recently proposed hybrid CTC/attention architecture for audio-visual recognition of speech in-the-wild. To the best of our knowledge, this is the first time that such a hybrid architecture architecture is used for audio-visual recognition of speech. We use the LRS2 database and show that the proposed audio-visual model leads to an 1.3% absolute decrease in word error rate over the audio-only model and achieves the new state-of-the-art performance on LRS2 database (7% word error rate). We also observe that the audio-visual model significantly outperforms the audio-based model (up to 32.9% absolute improvement in word error rate) for several different types of noise as the signal-to-noise ratio decreases.
Stavros Petridis, Themos Stafylakis, Pingchuan Ma et al.
Several end-to-end deep learning approaches have been recently presented which extract either audio or visual features from the input images or audio signals and perform speech recognition. However, research on end-to-end audiovisual models is very limited. In this work, we present an end-to-end audiovisual model based on residual networks and Bidirectional Gated Recurrent Units (BGRUs). To the best of our knowledge, this is the first audiovisual fusion model which simultaneously learns to extract features directly from the image pixels and audio waveforms and performs within-context word recognition on a large publicly available dataset (LRW). The model consists of two streams, one for each modality, which extract features directly from mouth regions and raw waveforms. The temporal dynamics in each stream/modality are modeled by a 2-layer BGRU and the fusion of multiple streams/modalities takes place via another 2-layer BGRU. A slight improvement in the classification rate over an end-to-end audio-only and MFCC-based model is reported in clean audio conditions and low levels of noise. In presence of high levels of noise, the end-to-end audiovisual model significantly outperforms both audio-only models.