Ehsan Adeli

Anirudh Sriram, Adrien Gaidon, Jiajun Wu et al. · salesforce, stanford

Recent advances in self-supervised representation learning have enabled more efficient and robust model performance without relying on extensive labeled data. However, most works are still focused on images, with few working on videos and even fewer on multi-view videos, where more powerful inductive biases can be leveraged for self-supervision. In this work, we propose a novel method for representation learning of multi-view videos, where we explicitly model the representation space to maintain Homography Equivariance (HomE). Our method learns an implicit mapping between different views, culminating in a representation space that maintains the homography relationship between neighboring views. We evaluate our HomE representation via action recognition and pedestrian intent prediction as downstream tasks. On action classification, our method obtains 96.4% 3-fold accuracy on the UCF101 dataset, better than most state-of-the-art self-supervised learning methods. Similarly, on the STIP dataset, we outperform the state-of-the-art by 6% for pedestrian intent prediction one second into the future while also obtaining an accuracy of 91.2% for pedestrian action (cross vs. not-cross) classification. Code is available at https://github.com/anirudhs123/HomE.

Reza Azad, Ehsan Khodapanah Aghdam, Amelie Rauland et al.

Automatic medical image segmentation is a crucial topic in the medical domain and successively a critical counterpart in the computer-aided diagnosis paradigm. U-Net is the most widespread image segmentation architecture due to its flexibility, optimized modular design, and success in all medical image modalities. Over the years, the U-Net model achieved tremendous attention from academic and industrial researchers. Several extensions of this network have been proposed to address the scale and complexity created by medical tasks. Addressing the deficiency of the naive U-Net model is the foremost step for vendors to utilize the proper U-Net variant model for their business. Having a compendium of different variants in one place makes it easier for builders to identify the relevant research. Also, for ML researchers it will help them understand the challenges of the biological tasks that challenge the model. To address this, we discuss the practical aspects of the U-Net model and suggest a taxonomy to categorize each network variant. Moreover, to measure the performance of these strategies in a clinical application, we propose fair evaluations of some unique and famous designs on well-known datasets. We provide a comprehensive implementation library with trained models for future research. In addition, for ease of future studies, we created an online list of U-Net papers with their possible official implementation. All information is gathered in https://github.com/NITR098/Awesome-U-Net repository.

Mark Endo, Kathleen L. Poston, Edith V. Sullivan et al.

Parkinson's disease (PD) is a neurological disorder that has a variety of observable motor-related symptoms such as slow movement, tremor, muscular rigidity, and impaired posture. PD is typically diagnosed by evaluating the severity of motor impairments according to scoring systems such as the Movement Disorder Society Unified Parkinson's Disease Rating Scale (MDS-UPDRS). Automated severity prediction using video recordings of individuals provides a promising route for non-intrusive monitoring of motor impairments. However, the limited size of PD gait data hinders model ability and clinical potential. Because of this clinical data scarcity and inspired by the recent advances in self-supervised large-scale language models like GPT-3, we use human motion forecasting as an effective self-supervised pre-training task for the estimation of motor impairment severity. We introduce GaitForeMer, Gait Forecasting and impairment estimation transforMer, which is first pre-trained on public datasets to forecast gait movements and then applied to clinical data to predict MDS-UPDRS gait impairment severity. Our method outperforms previous approaches that rely solely on clinical data by a large margin, achieving an F1 score of 0.76, precision of 0.79, and recall of 0.75. Using GaitForeMer, we show how public human movement data repositories can assist clinical use cases through learning universal motion representations. The code is available at https://github.com/markendo/GaitForeMer .

Reza Azad, Moein Heidari, Moein Shariatnia et al.

Convolutional neural networks (CNNs) have been the de facto standard in a diverse set of computer vision tasks for many years. Especially, deep neural networks based on seminal architectures such as U-shaped models with skip-connections or atrous convolution with pyramid pooling have been tailored to a wide range of medical image analysis tasks. The main advantage of such architectures is that they are prone to detaining versatile local features. However, as a general consensus, CNNs fail to capture long-range dependencies and spatial correlations due to the intrinsic property of confined receptive field size of convolution operations. Alternatively, Transformer, profiting from global information modelling that stems from the self-attention mechanism, has recently attained remarkable performance in natural language processing and computer vision. Nevertheless, previous studies prove that both local and global features are critical for a deep model in dense prediction, such as segmenting complicated structures with disparate shapes and configurations. To this end, this paper proposes TransDeepLab, a novel DeepLab-like pure Transformer for medical image segmentation. Specifically, we exploit hierarchical Swin-Transformer with shifted windows to extend the DeepLabv3 and model the Atrous Spatial Pyramid Pooling (ASPP) module. A thorough search of the relevant literature yielded that we are the first to model the seminal DeepLab model with a pure Transformer-based model. Extensive experiments on various medical image segmentation tasks verify that our approach performs superior or on par with most contemporary works on an amalgamation of Vision Transformer and CNN-based methods, along with a significant reduction of model complexity. The codes and trained models are publicly available at https://github.com/rezazad68/transdeeplab

Tiange Xiang, Adam Sun, Jiajun Wu et al. · stanford

3D understanding and rendering of moving humans from monocular videos is a challenging task. Despite recent progress, the task remains difficult in real-world scenarios, where obstacles may block the camera view and cause partial occlusions in the captured videos. Existing methods cannot handle such defects due to two reasons. First, the standard rendering strategy relies on point-point mapping, which could lead to dramatic disparities between the visible and occluded areas of the body. Second, the naive direct regression approach does not consider any feasibility criteria (ie, prior information) for rendering under occlusions. To tackle the above drawbacks, we present OccNeRF, a neural rendering method that achieves better rendering of humans in severely occluded scenes. As direct solutions to the two drawbacks, we propose surface-based rendering by integrating geometry and visibility priors. We validate our method on both simulated and real-world occlusions and demonstrate our method's superiority.

Carlos Hinojosa, Miguel Marquez, Henry Arguello et al. · salesforce, stanford

The accelerated use of digital cameras prompts an increasing concern about privacy and security, particularly in applications such as action recognition. In this paper, we propose an optimizing framework to provide robust visual privacy protection along the human action recognition pipeline. Our framework parameterizes the camera lens to successfully degrade the quality of the videos to inhibit privacy attributes and protect against adversarial attacks while maintaining relevant features for activity recognition. We validate our approach with extensive simulations and hardware experiments.

Reza Azad, Moein Heidari, Julien Cohen-Adad et al.

Accurate and automatic segmentation of intervertebral discs from medical images is a critical task for the assessment of spine-related diseases such as osteoporosis, vertebral fractures, and intervertebral disc herniation. To date, various approaches have been developed in the literature which routinely relies on detecting the discs as the primary step. A disadvantage of many cohort studies is that the localization algorithm also yields false-positive detections. In this study, we aim to alleviate this problem by proposing a novel U-Net-based structure to predict a set of candidates for intervertebral disc locations. In our design, we integrate the image shape information (image gradients) to encourage the model to learn rich and generic geometrical information. This additional signal guides the model to selectively emphasize the contextual representation and suppress the less discriminative features. On the post-processing side, to further decrease the false positive rate, we propose a permutation invariant 'look once' model, which accelerates the candidate recovery procedure. In comparison with previous studies, our proposed approach does not need to perform the selection in an iterative fashion. The proposed method was evaluated on the spine generic public multi-center dataset and demonstrated superior performance compared to previous work. We have provided the implementation code in https://github.com/rezazad68/intervertebral-lookonce

Favour Nerrise, Qingyu Zhao, Kathleen L. Poston et al.

One of the hallmark symptoms of Parkinson's Disease (PD) is the progressive loss of postural reflexes, which eventually leads to gait difficulties and balance problems. Identifying disruptions in brain function associated with gait impairment could be crucial in better understanding PD motor progression, thus advancing the development of more effective and personalized therapeutics. In this work, we present an explainable, geometric, weighted-graph attention neural network (xGW-GAT) to identify functional networks predictive of the progression of gait difficulties in individuals with PD. xGW-GAT predicts the multi-class gait impairment on the MDS Unified PD Rating Scale (MDS-UPDRS). Our computational- and data-efficient model represents functional connectomes as symmetric positive definite (SPD) matrices on a Riemannian manifold to explicitly encode pairwise interactions of entire connectomes, based on which we learn an attention mask yielding individual- and group-level explainability. Applied to our resting-state functional MRI (rs-fMRI) dataset of individuals with PD, xGW-GAT identifies functional connectivity patterns associated with gait impairment in PD and offers interpretable explanations of functional subnetworks associated with motor impairment. Our model successfully outperforms several existing methods while simultaneously revealing clinically-relevant connectivity patterns. The source code is available at https://github.com/favour-nerrise/xGW-GAT .

Jiahong Ouyang, Qingyu Zhao, Ehsan Adeli et al.

Interpretability is a key issue when applying deep learning models to longitudinal brain MRIs. One way to address this issue is by visualizing the high-dimensional latent spaces generated by deep learning via self-organizing maps (SOM). SOM separates the latent space into clusters and then maps the cluster centers to a discrete (typically 2D) grid preserving the high-dimensional relationship between clusters. However, learning SOM in a high-dimensional latent space tends to be unstable, especially in a self-supervision setting. Furthermore, the learned SOM grid does not necessarily capture clinically interesting information, such as brain age. To resolve these issues, we propose the first self-supervised SOM approach that derives a high-dimensional, interpretable representation stratified by brain age solely based on longitudinal brain MRIs (i.e., without demographic or cognitive information). Called Longitudinally-consistent Self-Organized Representation learning (LSOR), the method is stable during training as it relies on soft clustering (vs. the hard cluster assignments used by existing SOM). Furthermore, our approach generates a latent space stratified according to brain age by aligning trajectories inferred from longitudinal MRIs to the reference vector associated with the corresponding SOM cluster. When applied to longitudinal MRIs of the Alzheimer's Disease Neuroimaging Initiative (ADNI, N=632), LSOR generates an interpretable latent space and achieves comparable or higher accuracy than the state-of-the-art representations with respect to the downstream tasks of classification (static vs. progressive mild cognitive impairment) and regression (determining ADAS-Cog score of all subjects). The code is available at https://github.com/ouyangjiahong/longitudinal-som-single-modality.

Magdalini Paschali, Qingyu Zhao, Ehsan Adeli et al. · stanford

A fundamental approach in neuroscience research is to test hypotheses based on neuropsychological and behavioral measures, i.e., whether certain factors (e.g., related to life events) are associated with an outcome (e.g., depression). In recent years, deep learning has become a potential alternative approach for conducting such analyses by predicting an outcome from a collection of factors and identifying the most "informative" ones driving the prediction. However, this approach has had limited impact as its findings are not linked to statistical significance of factors supporting hypotheses. In this article, we proposed a flexible and scalable approach based on the concept of permutation testing that integrates hypothesis testing into the data-driven deep learning analysis. We apply our approach to the yearly self-reported assessments of 621 adolescent participants of the National Consortium of Alcohol and Neurodevelopment in Adolescence (NCANDA) to predict negative valence, a symptom of major depressive disorder according to the NIMH Research Domain Criteria (RDoC). Our method successfully identifies categories of risk factors that further explain the symptom.

Stephen Su, Samuel Kwong, Qingyu Zhao et al. · salesforce, stanford

There has been an increasing interest in multi-task learning for video understanding in recent years. In this work, we propose a generalized notion of multi-task learning by incorporating both auxiliary tasks that the model should perform well on and adversarial tasks that the model should not perform well on. We employ Necessary Condition Analysis (NCA) as a data-driven approach for deciding what category these tasks should fall in. Our novel proposed framework, Adversarial Multi-Task Neural Networks (AMT), penalizes adversarial tasks, determined by NCA to be scene recognition in the Holistic Video Understanding (HVU) dataset, to improve action recognition. This upends the common assumption that the model should always be encouraged to do well on all tasks in multi-task learning. Simultaneously, AMT still retains all the benefits of multi-task learning as a generalization of existing methods and uses object recognition as an auxiliary task to aid action recognition. We introduce two challenging Scene-Invariant test splits of HVU, where the model is evaluated on action-scene co-occurrences not encountered in training. We show that our approach improves accuracy by ~3% and encourages the model to attend to action features instead of correlation-biasing scene features.

Jieneng Chen, Jieru Mei, Xianhang Li et al.

Medical image segmentation plays a crucial role in advancing healthcare systems for disease diagnosis and treatment planning. The u-shaped architecture, popularly known as U-Net, has proven highly successful for various medical image segmentation tasks. However, U-Net's convolution-based operations inherently limit its ability to model long-range dependencies effectively. To address these limitations, researchers have turned to Transformers, renowned for their global self-attention mechanisms, as alternative architectures. One popular network is our previous TransUNet, which leverages Transformers' self-attention to complement U-Net's localized information with the global context. In this paper, we extend the 2D TransUNet architecture to a 3D network by building upon the state-of-the-art nnU-Net architecture, and fully exploring Transformers' potential in both the encoder and decoder design. We introduce two key components: 1) A Transformer encoder that tokenizes image patches from a convolution neural network (CNN) feature map, enabling the extraction of global contexts, and 2) A Transformer decoder that adaptively refines candidate regions by utilizing cross-attention between candidate proposals and U-Net features. Our investigations reveal that different medical tasks benefit from distinct architectural designs. The Transformer encoder excels in multi-organ segmentation, where the relationship among organs is crucial. On the other hand, the Transformer decoder proves more beneficial for dealing with small and challenging segmented targets such as tumor segmentation. Extensive experiments showcase the significant potential of integrating a Transformer-based encoder and decoder into the u-shaped medical image segmentation architecture. TransUNet outperforms competitors in various medical applications.

Kamran Alipour, Aditya Lahiri, Ehsan Adeli et al.

Despite their high accuracies, modern complex image classifiers cannot be trusted for sensitive tasks due to their unknown decision-making process and potential biases. Counterfactual explanations are very effective in providing transparency for these black-box algorithms. Nevertheless, generating counterfactuals that can have a consistent impact on classifier outputs and yet expose interpretable feature changes is a very challenging task. We introduce a novel method to generate causal and yet interpretable counterfactual explanations for image classifiers using pretrained generative models without any re-training or conditioning. The generative models in this technique are not bound to be trained on the same data as the target classifier. We use this framework to obtain contrastive and causal sufficiency and necessity scores as global explanations for black-box classifiers. On the task of face attribute classification, we show how different attributes influence the classifier output by providing both causal and contrastive feature attributions, and the corresponding counterfactual images.

Ehsan Adeli, Luning Sun, Jianxun Wang et al.

In this research paper, we study the capability of artificial neural network models to emulate storm surge based on the storm track/size/intensity history, leveraging a database of synthetic storm simulations. Traditionally, Computational Fluid Dynamics solvers are employed to numerically solve the storm surge governing equations that are Partial Differential Equations and are generally very costly to simulate. This study presents a neural network model that can predict storm surge, informed by a database of synthetic storm simulations. This model can serve as a fast and affordable emulator for the very expensive CFD solvers. The neural network model is trained with the storm track parameters used to drive the CFD solvers, and the output of the model is the time-series evolution of the predicted storm surge across multiple nodes within the spatial domain of interest. Once the model is trained, it can be deployed for further predictions based on new storm track inputs. The developed neural network model is a time-series model, a Long short-term memory, a variation of Recurrent Neural Network, which is enriched with Convolutional Neural Networks. The convolutional neural network is employed to capture the correlation of data spatially. Therefore, the temporal and spatial correlations of data are captured by the combination of the mentioned models, the ConvLSTM model. As the problem is a sequence to sequence time-series problem, an encoder-decoder ConvLSTM model is designed. Some other techniques in the process of model training are also employed to enrich the model performance. The results show the proposed convolutional recurrent neural network outperforms the Gaussian Process implementation for the examined synthetic storm database.

Yueting Li, Qingyue Wei, Ehsan Adeli et al.

The white-matter (micro-)structural architecture of the brain promotes synchrony among neuronal populations, giving rise to richly patterned functional connections. A fundamental problem for systems neuroscience is determining the best way to relate structural and functional networks quantified by diffusion tensor imaging and resting-state functional MRI. As one of the state-of-the-art approaches for network analysis, graph convolutional networks (GCN) have been separately used to analyze functional and structural networks, but have not been applied to explore inter-network relationships. In this work, we propose to couple the two networks of an individual by adding inter-network edges between corresponding brain regions, so that the joint structure-function graph can be directly analyzed by a single GCN. The weights of inter-network edges are learnable, reflecting non-uniform structure-function coupling strength across the brain. We apply our Joint-GCN to predict age and sex of 662 participants from the public dataset of the National Consortium on Alcohol and Neurodevelopment in Adolescence (NCANDA) based on their functional and micro-structural white-matter networks. Our results support that the proposed Joint-GCN outperforms existing multi-modal graph learning approaches for analyzing structural and functional networks.

Wei Peng, Tomas Bosschieter, Jiahong Ouyang et al.

Generative AI models hold great potential in creating synthetic brain MRIs that advance neuroimaging studies by, for example, enriching data diversity. However, the mainstay of AI research only focuses on optimizing the visual quality (such as signal-to-noise ratio) of the synthetic MRIs while lacking insights into their relevance to neuroscience. To gain these insights with respect to T1-weighted MRIs, we first propose a new generative model, BrainSynth, to synthesize metadata-conditioned (e.g., age- and sex-specific) MRIs that achieve state-of-the-art visual quality. We then extend our evaluation with a novel procedure to quantify anatomical plausibility, i.e., how well the synthetic MRIs capture macrostructural properties of brain regions, and how accurately they encode the effects of age and sex. Results indicate that more than half of the brain regions in our synthetic MRIs are anatomically accurate, i.e., with a small effect size between real and synthetic MRIs. Moreover, the anatomical plausibility varies across cortical regions according to their geometric complexity. As is, our synthetic MRIs can significantly improve the training of a Convolutional Neural Network to identify accelerated aging effects in an independent study. These results highlight the opportunities of using generative AI to aid neuroimaging research and point to areas for further improvement.

Anthony Vento, Qingyu Zhao, Robert Paul et al.

Translating machine learning algorithms into clinical applications requires addressing challenges related to interpretability, such as accounting for the effect of confounding variables (or metadata). Confounding variables affect the relationship between input training data and target outputs. When we train a model on such data, confounding variables will bias the distribution of the learned features. A recent promising solution, MetaData Normalization (MDN), estimates the linear relationship between the metadata and each feature based on a non-trainable closed-form solution. However, this estimation is confined by the sample size of a mini-batch and thereby may cause the approach to be unstable during training. In this paper, we extend the MDN method by applying a Penalty approach (referred to as PDMN). We cast the problem into a bi-level nested optimization problem. We then approximate this optimization problem using a penalty method so that the linear parameters within the MDN layer are trainable and learned on all samples. This enables PMDN to be plugged into any architectures, even those unfit to run batch-level operations, such as transformers and recurrent models. We show improvement in model accuracy and greater independence from confounders using PMDN over MDN in a synthetic experiment and a multi-label, multi-site dataset of magnetic resonance images (MRIs).

Pavel Jahoda, Azade Farshad, Yousef Yeganeh et al.

Scene graphs have emerged as accurate descriptive priors for image generation and manipulation tasks, however, their complexity and diversity of the shapes and relations of objects in data make it challenging to incorporate them into the models and generate high-quality results. To address these challenges, we propose PRISM, a novel progressive multi-head image manipulation approach to improve the accuracy and quality of the manipulated regions in the scene. Our image manipulation framework is trained using an end-to-end denoising masked reconstruction proxy task, where the masked regions are progressively unmasked from the outer regions to the inner part. We take advantage of the outer part of the masked area as they have a direct correlation with the context of the scene. Moreover, our multi-head architecture simultaneously generates detailed object-specific regions in addition to the entire image to produce higher-quality images. Our model outperforms the state-of-the-art methods in the semantic image manipulation task on the CLEVR and Visual Genome datasets. Our results demonstrate the potential of our approach for enhancing the quality and precision of scene graph-based image manipulation.

Mohammad Eslami, Solale Tabarestani, Ehsan Adeli et al.

With the advent of sophisticated machine learning (ML) techniques and the promising results they yield, especially in medical applications, where they have been investigated for different tasks to enhance the decision-making process. Since visualization is such an effective tool for human comprehension, memorization, and judgment, we have presented a first-of-its-kind estimation approach we refer to as Visualized Learning for Machine Learning (VL4ML) that not only can serve to assist physicians and clinicians in making reasoned medical decisions, but it also allows to appreciate the uncertainty visualization, which could raise incertitude in making the appropriate classification or prediction. For the proof of concept, and to demonstrate the generalized nature of this visualized estimation approach, five different case studies are examined for different types of tasks including classification, regression, and longitudinal prediction. A survey analysis with more than 100 individuals is also conducted to assess users' feedback on this visualized estimation method. The experiments and the survey demonstrate the practical merits of the VL4ML that include: (1) appreciating visually clinical/medical estimations; (2) getting closer to the patients' preferences; (3) improving doctor-patient communication, and (4) visualizing the uncertainty introduced through the black box effect of the deployed ML algorithm. All the source codes are shared via a GitHub repository.

Edward Vendrow, Satyajit Kumar, Ehsan Adeli et al.

Human pose forecasting is a challenging problem involving complex human body motion and posture dynamics. In cases that there are multiple people in the environment, one's motion may also be influenced by the motion and dynamic movements of others. Although there are several previous works targeting the problem of multi-person dynamic pose forecasting, they often model the entire pose sequence as time series (ignoring the underlying relationship between joints) or only output the future pose sequence of one person at a time. In this paper, we present a new method, called Social Motion Transformer (SoMoFormer), for multi-person 3D pose forecasting. Our transformer architecture uniquely models human motion input as a joint sequence rather than a time sequence, allowing us to perform attention over joints while predicting an entire future motion sequence for each joint in parallel. We show that with this problem reformulation, SoMoFormer naturally extends to multi-person scenes by using the joints of all people in a scene as input queries. Using learned embeddings to denote the type of joint, person identity, and global position, our model learns the relationships between joints and between people, attending more strongly to joints from the same or nearby people. SoMoFormer outperforms state-of-the-art methods for long-term motion prediction on the SoMoF benchmark as well as the CMU-Mocap and MuPoTS-3D datasets. Code will be made available after publication.

Yousef Yeganeh, Azade Farshad, Peter Weinberger et al.

Although purely transformer-based architectures showed promising performance in many computer vision tasks, many hybrid models consisting of CNN and transformer blocks are introduced to fit more specialized tasks. Nevertheless, despite the performance gain of both pure and hybrid transformer-based architectures compared to CNNs in medical imaging segmentation, their high training cost and complexity make it challenging to use them in real scenarios. In this work, we propose simple architectures based on purely convolutional layers, and show that by just taking advantage of the attention map visualizations obtained from a self-supervised pretrained vision transformer network (e.g., DINO) one can outperform complex transformer-based networks with much less computation costs. The proposed architecture is composed of two encoder branches with the original image as input in one branch and the attention map visualizations of the same image from multiple self-attention heads from a pre-trained DINO model (as multiple channels) in the other branch. The results of our experiments on two publicly available medical imaging datasets show that the proposed pipeline outperforms U-Net and the state-of-the-art medical image segmentation models.

Yixin Wang, Wei Peng, Yu Zhang et al.

Many longitudinal neuroimaging studies aim to improve the understanding of brain aging and diseases by studying the dynamic interactions between brain function and cognition. Doing so requires accurate encoding of their multidimensional relationship while accounting for individual variability over time. For this purpose, we propose an unsupervised learning model (called \underline{\textbf{Co}}ntrastive Learning-based \underline{\textbf{Gra}}ph Generalized \underline{\textbf{Ca}}nonical Correlation Analysis (CoGraCa)) that encodes their relationship via Graph Attention Networks and generalized Canonical Correlational Analysis. To create brain-cognition fingerprints reflecting unique neural and cognitive phenotype of each person, the model also relies on individualized and multimodal contrastive learning. We apply CoGraCa to longitudinal dataset of healthy individuals consisting of resting-state functional MRI and cognitive measures acquired at multiple visits for each participant. The generated fingerprints effectively capture significant individual differences and outperform current single-modal and CCA-based multimodal models in identifying sex and age. More importantly, our encoding provides interpretable interactions between those two modalities.

Sven Lüpke, Yousef Yeganeh, Ehsan Adeli et al.

Recent advances in generative models for medical imaging have shown promise in representing multiple modalities. However, the variability in modality availability across datasets limits the general applicability of the synthetic data they produce. To address this, we present a novel physics-informed generative model capable of synthesizing a variable number of brain MRI modalities, including those not present in the original dataset. Our approach utilizes latent diffusion models and a two-step generative process: first, unobserved physical tissue property maps are synthesized using a latent diffusion model, and then these maps are combined with a physical signal model to generate the final MRI scan. Our experiments demonstrate the efficacy of this approach in generating unseen MR contrasts and preserving physical plausibility. Furthermore, we validate the distributions of generated tissue properties by comparing them to those measured in real brain tissue.

Yousef Yeganeh, Azade Farshad, Goktug Guevercin et al.

Although the preservation of shape continuity and physiological anatomy is a natural assumption in the segmentation of medical images, it is often neglected by deep learning methods that mostly aim for the statistical modeling of input data as pixels rather than interconnected structures. In biological structures, however, organs are not separate entities; for example, in reality, a severed vessel is an indication of an underlying problem, but traditional segmentation models are not designed to strictly enforce the continuity of anatomy, potentially leading to inaccurate medical diagnoses. To address this issue, we propose a graph-based approach that enforces the continuity and connectivity of anatomical topology in medical images. Our method encodes the continuity of shapes as a graph constraint, ensuring that the network's predictions maintain this continuity. We evaluate our method on two public benchmarks on retinal vessel segmentation, showing significant improvements in connectivity metrics compared to traditional methods while getting better or on-par performance on segmentation metrics.

Yue Zhao, Hanwen Jiang, Zhenlin Xu et al.

Non-parametric quantization has received much attention due to its efficiency on parameters and scalability to a large codebook. In this paper, we present a unified formulation of different non-parametric quantization methods through the lens of lattice coding. The geometry of lattice codes explains the necessity of auxiliary loss terms when training auto-encoders with certain existing lookup-free quantization variants such as BSQ. As a step forward, we explore a few possible candidates, including random lattices, generalized Fibonacci lattices, and densest sphere packing lattices. Among all, we find the Leech lattice-based quantization method, which is dubbed as Spherical Leech Quantization ($Λ_{24}$-SQ), leads to both a simplified training recipe and an improved reconstruction-compression tradeoff thanks to its high symmetry and even distribution on the hypersphere. In image tokenization and compression tasks, this quantization approach achieves better reconstruction quality across all metrics than BSQ, the best prior art, while consuming slightly fewer bits. The improvement also extends to state-of-the-art auto-regressive image generation frameworks.

Aditya Lahiri, Kamran Alipour, Ehsan Adeli et al.

With the widespread use of sophisticated machine learning models in sensitive applications, understanding their decision-making has become an essential task. Models trained on tabular data have witnessed significant progress in explanations of their underlying decision making processes by virtue of having a small number of discrete features. However, applying these methods to high-dimensional inputs such as images is not a trivial task. Images are composed of pixels at an atomic level and do not carry any interpretability by themselves. In this work, we seek to use annotated high-level interpretable features of images to provide explanations. We leverage the Shapley value framework from Game Theory, which has garnered wide acceptance in general XAI problems. By developing a pipeline to generate counterfactuals and subsequently using it to estimate Shapley values, we obtain contrastive and interpretable explanations with strong axiomatic guarantees.

Yanchen Wang, Adam Turnbull, Yunlong Xu et al.

Computerized cognitive training (CCT) is a scalable, well-tolerated intervention that has promise for slowing cognitive decline. Outcomes from CCT are limited by a lack of effective engagement, which is decreased by factors such as mental fatigue, particularly in older adults at risk for dementia. There is a need for scalable, automated measures that can monitor mental fatigue during CCT. Here, we develop and validate a novel Recurrent Video Transformer (RVT) method for monitoring real-time mental fatigue in older adults with mild cognitive impairment from video-recorded facial gestures during CCT. The RVT model achieved the highest balanced accuracy(78%) and precision (0.82) compared to the prior state-of-the-art models for binary and multi-class classification of mental fatigue and was additionally validated via significant association (p=0.023) with CCT reaction time. By leveraging dynamic temporal information, the RVT model demonstrates the potential to accurately measure real-time mental fatigue, laying the foundation for future personalized CCT that increase effective engagement.

Noriyuki Kugo, Xiang Li, Zixin Li et al.

Video Question Answering (VQA) inherently relies on multimodal reasoning, integrating visual, temporal, and linguistic cues to achieve a deeper understanding of video content. However, many existing methods rely on feeding frame-level captions into a single model, making it difficult to adequately capture temporal and interactive contexts. To address this limitation, we introduce VideoMultiAgents, a framework that integrates specialized agents for vision, scene graph analysis, and text processing. It enhances video understanding leveraging complementary multimodal reasoning from independently operating agents. Our approach is also supplemented with a question-guided caption generation, which produces captions that highlight objects, actions, and temporal transitions directly relevant to a given query, thus improving the answer accuracy. Experimental results demonstrate that our method achieves state-of-the-art performance on Intent-QA (79.0%, +6.2% over previous SOTA), EgoSchema subset (75.4%, +3.4%), and NExT-QA (79.6%, +0.4%). The source code is available at https://github.com/PanasonicConnect/VideoMultiAgents.

Haokai Zhao, Haowei Lou, Lina Yao et al.

Computational neuroimaging involves analyzing brain images or signals to provide mechanistic insights and predictive tools for human cognition and behavior. While diffusion models have shown stability and high-quality generation in natural images, there is increasing interest in adapting them to analyze brain data for various neurological tasks such as data enhancement, disease diagnosis and brain decoding. This survey provides an overview of recent efforts to integrate diffusion models into computational neuroimaging. We begin by introducing the common neuroimaging data modalities, follow with the diffusion formulations and conditioning mechanisms. Then we discuss how the variations of the denoising starting point, condition input and generation target of diffusion models are developed and enhance specific neuroimaging tasks. For a comprehensive overview of the ongoing research, we provide a publicly available repository at https://github.com/JoeZhao527/dm4neuro.

Juze Zhang, Changan Chen, Xin Chen et al.

Human communication is inherently multimodal and social: words, prosody, and body language jointly carry intent. Yet most prior systems model human behavior as a translation task co-speech gesture or text-to-motion that maps a fixed utterance to motion clips-without requiring agentic decision-making about when to move, what to do, or how to adapt across multi-turn dialogue. This leads to brittle timing, weak social grounding, and fragmented stacks where speech, text, and motion are trained or inferred in isolation. We introduce ViBES (Voice in Behavioral Expression and Synchrony), a conversational 3D agent that jointly plans language and movement and executes dialogue-conditioned body actions. Concretely, ViBES is a speech-language-behavior (SLB) model with a mixture-of-modality-experts (MoME) backbone: modality-partitioned transformer experts for speech, facial expression, and body motion. The model processes interleaved multimodal token streams with hard routing by modality (parameters are split per expert), while sharing information through cross-expert attention. By leveraging strong pretrained speech-language models, the agent supports mixed-initiative interaction: users can speak, type, or issue body-action directives mid-conversation, and the system exposes controllable behavior hooks for streaming responses. We further benchmark on multi-turn conversation with automatic metrics of dialogue-motion alignment and behavior quality, and observe consistent gains over strong co-speech and text-to-motion baselines. ViBES goes beyond "speech-conditioned motion generation" toward agentic virtual bodies where language, prosody, and movement are jointly generated, enabling controllable, socially competent 3D interaction. Code and data will be made available at: ai.stanford.edu/~juze/ViBES/

Yao He, Youngjoong Kwon, Tiange Xiang et al.

We present a framework that adapts 2D diffusion models for 3D shape completion from incomplete point clouds. While text-to-image diffusion models have achieved remarkable success with abundant 2D data, 3D diffusion models lag due to the scarcity of high-quality 3D datasets and a persistent modality gap between 3D inputs and 2D latent spaces. To overcome these limitations, we introduce the Shape Atlas, a compact 2D representation of 3D geometry that (1) enables full utilization of the generative power of pretrained 2D diffusion models, and (2) aligns the modalities between the conditional input and output spaces, allowing more effective conditioning. This unified 2D formulation facilitates learning from limited 3D data and produces high-quality, detail-preserving shape completions. We validate the effectiveness of our results on the PCN and ShapeNet-55 datasets. Additionally, we show the downstream application of creating artist-created meshes from our completed point clouds, further demonstrating the practicality of our method.

Shizhe He, Magdalini Paschali, Jiahong Ouyang et al. · stanford

Representation learning has become increasingly important, especially as powerful models have shifted towards learning latent representations before fine-tuning for downstream tasks. This approach is particularly valuable in leveraging the structural information within brain anatomy. However, a common limitation of recent models developed for MRIs is their tendency to ignore or remove geometric information, such as translation and rotation, thereby creating invariance with respect to geometric operations. We contend that incorporating knowledge about these geometric transformations into the model can significantly enhance its ability to learn more detailed anatomical information within brain structures. As a result, we propose a novel method for encoding 3D MRIs that enforces equivariance with respect to all rotations in 3D space, in other words, SO(3)-equivariance (SOE). By explicitly modeling this geometric equivariance in the representation space, we ensure that any rotational operation applied to the input image space is also reflected in the embedding representation space. This approach requires moving beyond traditional representation learning methods, as we need a representation vector space that allows for the application of the same SO(3) operation in that space. To facilitate this, we leverage the concept of vector neurons. The representation space formed by our method captures the brain's structural and anatomical information more effectively. We evaluate SOE pretrained on the structural MRIs of two public data sets with respect to the downstream task of predicting age and diagnosing Alzheimer's Disease from T1-weighted brain scans of the ADNI data set. We demonstrate that our approach not only outperforms other methods but is also robust against various degrees of rotation along different axes. The code is available at https://github.com/shizhehe/SOE-representation-learning.

Bahram Jafrasteh, Wei Peng, Cheng Wan et al.

Generative models enhance neuroimaging through data augmentation, quality improvement, and rare condition studies. Despite advances in realistic synthetic MRIs, evaluations focus on texture and perception, lacking sensitivity to crucial anatomical fidelity. This study proposes a new metric, called WASABI (Wasserstein-Based Anatomical Brain Index), to assess the anatomical realism of synthetic brain MRIs. WASABI leverages \textit{SynthSeg}, a deep learning-based brain parcellation tool, to derive volumetric measures of brain regions in each MRI and uses the multivariate Wasserstein distance to compare distributions between real and synthetic anatomies. Based on controlled experiments on two real datasets and synthetic MRIs from five generative models, WASABI demonstrates higher sensitivity in quantifying anatomical discrepancies compared to traditional image-level metrics, even when synthetic images achieve near-perfect visual quality. Our findings advocate for shifting the evaluation paradigm beyond visual inspection and conventional metrics, emphasizing anatomical fidelity as a crucial benchmark for clinically meaningful brain MRI synthesis. Our code is available at https://github.com/BahramJafrasteh/wasabi-mri.

Zane Durante, Robathan Harries, Edward Vendrow et al.

Understanding Activities of Daily Living (ADLs) is a crucial step for different applications including assistive robots, smart homes, and healthcare. However, to date, few benchmarks and methods have focused on complex ADLs, especially those involving multi-person interactions in home environments. In this paper, we propose a new dataset and benchmark, InteractADL, for understanding complex ADLs that involve interaction between humans (and objects). Furthermore, complex ADLs occurring in home environments comprise a challenging long-tailed distribution due to the rarity of multi-person interactions, and pose fine-grained visual recognition tasks due to the presence of semantically and visually similar classes. To address these issues, we propose a novel method for fine-grained few-shot video classification called Name Tuning that enables greater semantic separability by learning optimal class name vectors. We show that Name Tuning can be combined with existing prompt tuning strategies to learn the entire input text (rather than only learning the prompt or class names) and demonstrate improved performance for few-shot classification on InteractADL and 4 other fine-grained visual classification benchmarks. For transparency and reproducibility, we release our code at https://github.com/zanedurante/vlm_benchmark.

Liangqiong Qu, Yuyin Zhou, Paul Pu Liang et al.

Federated learning is an emerging research paradigm enabling collaborative training of machine learning models among different organizations while keeping data private at each institution. Despite recent progress, there remain fundamental challenges such as the lack of convergence and the potential for catastrophic forgetting across real-world heterogeneous devices. In this paper, we demonstrate that self-attention-based architectures (e.g., Transformers) are more robust to distribution shifts and hence improve federated learning over heterogeneous data. Concretely, we conduct the first rigorous empirical investigation of different neural architectures across a range of federated algorithms, real-world benchmarks, and heterogeneous data splits. Our experiments show that simply replacing convolutional networks with Transformers can greatly reduce catastrophic forgetting of previous devices, accelerate convergence, and reach a better global model, especially when dealing with heterogeneous data. We release our code and pretrained models at https://github.com/Liangqiong/ViT-FL-main to encourage future exploration in robust architectures as an alternative to current research efforts on the optimization front.

Jiahong Ouyang, Qingyu Zhao, Ehsan Adeli et al.

Longitudinal MRIs are often used to capture the gradual deterioration of brain structure and function caused by aging or neurological diseases. Analyzing this data via machine learning generally requires a large number of ground-truth labels, which are often missing or expensive to obtain. Reducing the need for labels, we propose a self-supervised strategy for representation learning named Longitudinal Neighborhood Embedding (LNE). Motivated by concepts in contrastive learning, LNE explicitly models the similarity between trajectory vectors across different subjects. We do so by building a graph in each training iteration defining neighborhoods in the latent space so that the progression direction of a subject follows the direction of its neighbors. This results in a smooth trajectory field that captures the global morphological change of the brain while maintaining the local continuity. We apply LNE to longitudinal T1w MRIs of two neuroimaging studies: a dataset composed of 274 healthy subjects, and Alzheimer's Disease Neuroimaging Initiative (ADNI, N=632). The visualization of the smooth trajectory vector field and superior performance on downstream tasks demonstrate the strength of the proposed method over existing self-supervised methods in extracting information associated with normal aging and in revealing the impact of neurodegenerative disorders. The code is available at \url{https://github.com/ouyangjiahong/longitudinal-neighbourhood-embedding.git}.

Jiahong Ouyang, Ehsan Adeli, Kilian M. Pohl et al.

Multi-modal MRIs are widely used in neuroimaging applications since different MR sequences provide complementary information about brain structures. Recent works have suggested that multi-modal deep learning analysis can benefit from explicitly disentangling anatomical (shape) and modality (appearance) information into separate image presentations. In this work, we challenge mainstream strategies by showing that they do not naturally lead to representation disentanglement both in theory and in practice. To address this issue, we propose a margin loss that regularizes the similarity in relationships of the representations across subjects and modalities. To enable robust training, we further use a conditional convolution to design a single model for encoding images of all modalities. Lastly, we propose a fusion function to combine the disentangled anatomical representations as a set of modality-invariant features for downstream tasks. We evaluate the proposed method on three multi-modal neuroimaging datasets. Experiments show that our proposed method can achieve superior disentangled representations compared to existing disentanglement strategies. Results also indicate that the fused anatomical representation has potential in the downstream task of zero-dose PET reconstruction and brain tumor segmentation. The code is available at \url{https://github.com/ouyangjiahong/representation-disentanglement}.

Jieneng Chen, Yongyi Lu, Qihang Yu et al.

Medical image segmentation is an essential prerequisite for developing healthcare systems, especially for disease diagnosis and treatment planning. On various medical image segmentation tasks, the u-shaped architecture, also known as U-Net, has become the de-facto standard and achieved tremendous success. However, due to the intrinsic locality of convolution operations, U-Net generally demonstrates limitations in explicitly modeling long-range dependency. Transformers, designed for sequence-to-sequence prediction, have emerged as alternative architectures with innate global self-attention mechanisms, but can result in limited localization abilities due to insufficient low-level details. In this paper, we propose TransUNet, which merits both Transformers and U-Net, as a strong alternative for medical image segmentation. On one hand, the Transformer encodes tokenized image patches from a convolution neural network (CNN) feature map as the input sequence for extracting global contexts. On the other hand, the decoder upsamples the encoded features which are then combined with the high-resolution CNN feature maps to enable precise localization. We argue that Transformers can serve as strong encoders for medical image segmentation tasks, with the combination of U-Net to enhance finer details by recovering localized spatial information. TransUNet achieves superior performances to various competing methods on different medical applications including multi-organ segmentation and cardiac segmentation. Code and models are available at https://github.com/Beckschen/TransUNet.

Mandy Lu, Kathleen Poston, Adolf Pfefferbaum et al.

Parkinson's disease (PD) is a progressive neurological disorder primarily affecting motor function resulting in tremor at rest, rigidity, bradykinesia, and postural instability. The physical severity of PD impairments can be quantified through the Movement Disorder Society Unified Parkinson's Disease Rating Scale (MDS-UPDRS), a widely used clinical rating scale. Accurate and quantitative assessment of disease progression is critical to developing a treatment that slows or stops further advancement of the disease. Prior work has mainly focused on dopamine transport neuroimaging for diagnosis or costly and intrusive wearables evaluating motor impairments. For the first time, we propose a computer vision-based model that observes non-intrusive video recordings of individuals, extracts their 3D body skeletons, tracks them through time, and classifies the movements according to the MDS-UPDRS gait scores. Experimental results show that our proposed method performs significantly better than chance and competing methods with an F1-score of 0.83 and a balanced accuracy of 81%. This is the first benchmark for classifying PD patients based on MDS-UPDRS gait severity and could be an objective biomarker for disease severity. Our work demonstrates how computer-assisted technologies can be used to non-intrusively monitor patients and their motor impairments. The code is available at https://github.com/mlu355/PD-Motor-Severity-Estimation.

Jiahong Ouyang, Qingyu Zhao, Edith V Sullivan et al.

Many neurological diseases are characterized by gradual deterioration of brain structure and function. Large longitudinal MRI datasets have revealed such deterioration, in part, by applying machine and deep learning to predict diagnosis. A popular approach is to apply Convolutional Neural Networks (CNN) to extract informative features from each visit of the longitudinal MRI and then use those features to classify each visit via Recurrent Neural Networks (RNNs). Such modeling neglects the progressive nature of the disease, which may result in clinically implausible classifications across visits. To avoid this issue, we propose to combine features across visits by coupling feature extraction with a novel longitudinal pooling layer and enforce consistency of the classification across visits in line with disease progression. We evaluate the proposed method on the longitudinal structural MRIs from three neuroimaging datasets: Alzheimer's Disease Neuroimaging Initiative (ADNI, N=404), a dataset composed of 274 normal controls and 329 patients with Alcohol Use Disorder (AUD), and 255 youths from the National Consortium on Alcohol and NeuroDevelopment in Adolescence (NCANDA). In all three experiments our method is superior to other widely used approaches for longitudinal classification thus making a unique contribution towards more accurate tracking of the impact of conditions on the brain. The code is available at https://github.com/ouyangjiahong/longitudinal-pooling.

Ehsan Adeli, Qingyu Zhao, Adolf Pfefferbaum et al.

Presence of bias (in datasets or tasks) is inarguably one of the most critical challenges in machine learning applications that has alluded to pivotal debates in recent years. Such challenges range from spurious associations between variables in medical studies to the bias of race in gender or face recognition systems. Controlling for all types of biases in the dataset curation stage is cumbersome and sometimes impossible. The alternative is to use the available data and build models incorporating fair representation learning. In this paper, we propose such a model based on adversarial training with two competing objectives to learn features that have (1) maximum discriminative power with respect to the task and (2) minimal statistical mean dependence with the protected (bias) variable(s). Our approach does so by incorporating a new adversarial loss function that encourages a vanished correlation between the bias and the learned features. We apply our method to synthetic data, medical images (containing task bias), and a dataset for gender classification (containing dataset bias). Our results show that the learned features by our method not only result in superior prediction performance but also are unbiased. The code is available at https://github.com/QingyuZhao/BR-Net/.

Hsu-kuang Chiu, Ehsan Adeli, Juan Carlos Niebles

Predicting the future is an important aspect for decision-making in robotics or autonomous driving systems, which heavily rely upon visual scene understanding. While prior work attempts to predict future video pixels, anticipate activities or forecast future scene semantic segments from segmentation of the preceding frames, methods that predict future semantic segmentation solely from the previous frame RGB data in a single end-to-end trainable model do not exist. In this paper, we propose a temporal encoder-decoder network architecture that encodes RGB frames from the past and decodes the future semantic segmentation. The network is coupled with a new knowledge distillation training framework specific for the forecasting task. Our method, only seeing preceding video frames, implicitly models the scene segments while simultaneously accounting for the object dynamics to infer the future scene semantic segments. Our results on Cityscapes and Apolloscape outperform the baseline and current state-of-the-art methods. Code is available at https://github.com/eddyhkchiu/segmenting_the_future/.

Hsu-kuang Chiu, Ehsan Adeli, Borui Wang et al.

Predicting and forecasting human dynamics is a very interesting but challenging task with several prospective applications in robotics, health-care, etc. Recently, several methods have been developed for human pose forecasting; however, they often introduce a number of limitations in their settings. For instance, previous work either focused only on short-term or long-term predictions, while sacrificing one or the other. Furthermore, they included the activity labels as part of the training process, and require them at testing time. These limitations confine the usage of pose forecasting models for real-world applications, as often there are no activity-related annotations for testing scenarios. In this paper, we propose a new action-agnostic method for short- and long-term human pose forecasting. To this end, we propose a new recurrent neural network for modeling the hierarchical and multi-scale characteristics of the human dynamics, denoted by triangular-prism RNN (TP-RNN). Our model captures the latent hierarchical structure embedded in temporal human pose sequences by encoding the temporal dependencies with different time-scales. For evaluation, we run an extensive set of experiments on Human 3.6M and Penn Action datasets and show that our method outperforms baseline and state-of-the-art methods quantitatively and qualitatively. Codes are available at https://github.com/eddyhkchiu/pose_forecast_wacv/

Seyyed Hossein Hasanpour, Mohammad Rouhani, Mohsen Fayyaz et al.

Major winning Convolutional Neural Networks (CNNs), such as VGGNet, ResNet, DenseNet, \etc, include tens to hundreds of millions of parameters, which impose considerable computation and memory overheads. This limits their practical usage in training and optimizing for real-world applications. On the contrary, light-weight architectures, such as SqueezeNet, are being proposed to address this issue. However, they mainly suffer from low accuracy, as they have compromised between the processing power and efficiency. These inefficiencies mostly stem from following an ad-hoc designing procedure. In this work, we discuss and propose several crucial design principles for an efficient architecture design and elaborate intuitions concerning different aspects of the design procedure. Furthermore, we introduce a new layer called {\it SAF-pooling} to improve the generalization power of the network while keeping it simple by choosing best features. Based on such principles, we propose a simple architecture called {\it SimpNet}. We empirically show that SimpNet provides a good trade-off between the computation/memory efficiency and the accuracy solely based on these primitive but crucial principles. SimpNet outperforms the deeper and more complex architectures such as VGGNet, ResNet, WideResidualNet \etc, on several well-known benchmarks, while having 2 to 25 times fewer number of parameters and operations. We obtain state-of-the-art results (in terms of a balance between the accuracy and the number of involved parameters) on standard datasets, such as CIFAR10, CIFAR100, MNIST and SVHN. The implementations are available at \href{url}{https://github.com/Coderx7/SimpNet}.

Yaser Souri, Erfan Noury, Ehsan Adeli

Visual attributes are great means of describing images or scenes, in a way both humans and computers understand. In order to establish a correspondence between images and to be able to compare the strength of each property between images, relative attributes were introduced. However, since their introduction, hand-crafted and engineered features were used to learn increasingly complex models for the problem of relative attributes. This limits the applicability of those methods for more realistic cases. We introduce a deep neural network architecture for the task of relative attribute prediction. A convolutional neural network (ConvNet) is adopted to learn the features by including an additional layer (ranking layer) that learns to rank the images based on these features. We adopt an appropriate ranking loss to train the whole network in an end-to-end fashion. Our proposed method outperforms the baseline and state-of-the-art methods in relative attribute prediction on various coarse and fine-grained datasets. Our qualitative results along with the visualization of the saliency maps show that the network is able to learn effective features for each specific attribute. Source code of the proposed method is available at https://github.com/yassersouri/ghiaseddin.

Soopil Kim, Sion An, Philip Chikontwe et al.

Logical anomalies (LA) refer to data violating underlying logical constraints e.g., the quantity, arrangement, or composition of components within an image. Detecting accurately such anomalies requires models to reason about various component types through segmentation. However, curation of pixel-level annotations for semantic segmentation is both time-consuming and expensive. Although there are some prior few-shot or unsupervised co-part segmentation algorithms, they often fail on images with industrial object. These images have components with similar textures and shapes, and a precise differentiation proves challenging. In this study, we introduce a novel component segmentation model for LA detection that leverages a few labeled samples and unlabeled images sharing logical constraints. To ensure consistent segmentation across unlabeled images, we employ a histogram matching loss in conjunction with an entropy loss. As segmentation predictions play a crucial role, we propose to enhance both local and global sample validity detection by capturing key aspects from visual semantics via three memory banks: class histograms, component composition embeddings and patch-level representations. For effective LA detection, we propose an adaptive scaling strategy to standardize anomaly scores from different memory banks in inference. Extensive experiments on the public benchmark MVTec LOCO AD reveal our method achieves 98.1% AUROC in LA detection vs. 89.6% from competing methods.

Zane Durante, Bidipta Sarkar, Ran Gong et al. · stanford

The development of artificial intelligence systems is transitioning from creating static, task-specific models to dynamic, agent-based systems capable of performing well in a wide range of applications. We propose an Interactive Agent Foundation Model that uses a novel multi-task agent training paradigm for training AI agents across a wide range of domains, datasets, and tasks. Our training paradigm unifies diverse pre-training strategies, including visual masked auto-encoders, language modeling, and next-action prediction, enabling a versatile and adaptable AI framework. We demonstrate the performance of our framework across three separate domains -- Robotics, Gaming AI, and Healthcare. Our model demonstrates its ability to generate meaningful and contextually relevant outputs in each area. The strength of our approach lies in its generality, leveraging a variety of data sources such as robotics sequences, gameplay data, large-scale video datasets, and textual information for effective multimodal and multi-task learning. Our approach provides a promising avenue for developing generalist, action-taking, multimodal systems.

Changan Chen, Juze Zhang, Shrinidhi K. Lakshmikanth et al.

Human communication is inherently multimodal, involving a combination of verbal and non-verbal cues such as speech, facial expressions, and body gestures. Modeling these behaviors is essential for understanding human interaction and for creating virtual characters that can communicate naturally in applications like games, films, and virtual reality. However, existing motion generation models are typically limited to specific input modalities -- either speech, text, or motion data -- and cannot fully leverage the diversity of available data. In this paper, we propose a novel framework that unifies verbal and non-verbal language using multimodal language models for human motion understanding and generation. This model is flexible in taking text, speech, and motion or any combination of them as input. Coupled with our novel pre-training strategy, our model not only achieves state-of-the-art performance on co-speech gesture generation but also requires much less data for training. Our model also unlocks an array of novel tasks such as editable gesture generation and emotion prediction from motion. We believe unifying the verbal and non-verbal language of human motion is essential for real-world applications, and language models offer a powerful approach to achieving this goal. Project page: languageofmotion.github.io.

Jensen Hwa, Qingyu Zhao, Aditya Lahiri et al.

Conditional independence (CI) constraints are critical for defining and evaluating fairness in machine learning, as well as for learning unconfounded or causal representations. Traditional methods for ensuring fairness either blindly learn invariant features with respect to a protected variable (e.g., race when classifying sex from face images) or enforce CI relative to the protected attribute only on the model output (e.g., the sex label). Neither of these methods are effective in enforcing CI in high-dimensional feature spaces. In this paper, we focus on a nascent approach characterizing the CI constraint in terms of two Jensen-Shannon divergence terms, and we extend it to high-dimensional feature spaces using a novel dynamic sampling strategy. In doing so, we introduce a new training paradigm that can be applied to any encoder architecture. We are able to enforce conditional independence of the diffusion autoencoder latent representation with respect to any protected attribute under the equalized odds constraint and show that this approach enables causal image generation with controllable latent spaces. Our experimental results demonstrate that our approach can achieve high accuracy on downstream tasks while upholding equality of odds.

Haoyu Chen, Hao Tang, Ehsan Adeli et al.

3D pose transfer that aims to transfer the desired pose to a target mesh is one of the most challenging 3D generation tasks. Previous attempts rely on well-defined parametric human models or skeletal joints as driving pose sources. However, to obtain those clean pose sources, cumbersome but necessary pre-processing pipelines are inevitable, hindering implementations of the real-time applications. This work is driven by the intuition that the robustness of the model can be enhanced by introducing adversarial samples into the training, leading to a more invulnerable model to the noisy inputs, which even can be further extended to directly handling the real-world data like raw point clouds/scans without intermediate processing. Furthermore, we propose a novel 3D pose Masked Autoencoder (3D-PoseMAE), a customized MAE that effectively learns 3D extrinsic presentations (i.e., pose). 3D-PoseMAE facilitates learning from the aspect of extrinsic attributes by simultaneously generating adversarial samples that perturb the model and learning the arbitrary raw noisy poses via a multi-scale masking strategy. Both qualitative and quantitative studies show that the transferred meshes given by our network result in much better quality. Besides, we demonstrate the strong generalizability of our method on various poses, different domains, and even raw scans. Experimental results also show meaningful insights that the intermediate adversarial samples generated in the training can successfully attack the existing pose transfer models.