Joseph JaJa’s research while affiliated with University of Maryland, College Park and other places

Automated mammography screening plays an important role in early breast cancer detection. However, current machine learning models, developed on some training datasets, may exhibit performance degradation and bias when deployed in real-world settings. In this paper, we analyze the performance of high-performing AI models on two mammography datasets-the Emory Breast Imaging Dataset (EMBED) and the RSNA 2022 challenge dataset. Specifically, we evaluate how these models perform across different subgroups, defined by six attributes, to detect potential biases using a range of classification metrics. Our analysis identifies certain subgroups that demonstrate notable underperformance, highlighting the need for ongoing monitoring of these subgroups' performance. To address this, we adopt a monitoring method designed to detect performance drifts over time. Upon identifying a drift, this method issues an alert, which can enable timely interventions. This approach not only provides a tool for tracking the performance but also helps ensure that AI models continue to perform effectively across diverse populations.

High-precision virtual environments are increasingly important for various education, simulation, training, performance, and entertainment applications. We present HoloCamera, an innovative volumetric capture instrument to rapidly acquire, process, and create cinematic-quality virtual avatars and scenarios. The HoloCamera consists of a custom-designed free-standing structure with 300 high-resolution RGB cameras mounted with uniform spacing spanning the four sides and the ceiling of a room-sized studio. The light field acquired from these cameras is streamed through a distributed array of GPUs that interleave the processing and transmission of 4K resolution images. The distributed compute infrastructure that powers these RGB cameras consists of 50 Jetson AGX Xavier boards, with each processing unit dedicated to driving and processing imagery from six cameras. A high-speed Gigabit Ethernet network fabric seamlessly interconnects all computing boards. In this systems paper, we provide an in-depth description of the steps involved and lessons learned in constructing such a cutting-edge volumetric capture facility that can be generalized to other such facilities. We delve into the techniques employed to achieve precise frame synchronization and spatial calibration of cameras, careful determination of angled camera mounts, image processing from the camera sensors, and the need for a resilient and robust network infrastructure. To advance the field of volumetric capture, we are releasing a high-fidelity static light-field dataset, which will serve as a benchmark for further research and applications of cinematic-quality volumetric light fields.

Generative modeling and self-supervised learning have in recent years made great strides towards learning from data in a completely unsupervised way. There is still however an open area of investigation into guiding a neural network to encode the data into representations that are interpretable or explainable. The problem of unsupervised disentanglement is of particular importance as it proposes to discover the different latent factors of variation or semantic concepts from the data alone, without labeled examples, and encode them into structurally disjoint latent representations. Without additional constraints or inductive biases placed in the network, a generative model may learn the data distribution and encode the factors, but not necessarily in a disentangled way. Here, we introduce a novel deep generative VAE-based model, ProtoVAE, that leverages a deep metric learning Prototypical network trained using self-supervision to impose these constraints. The prototypical network constrains the mapping of the representation space to data space to ensure that controlled changes in the representation space are mapped to changes in the factors of variations in the data space. Our model is completely unsupervised and requires no a priori knowledge of the dataset, including the number of factors. We evaluate our proposed model on the benchmark dSprites, 3DShapes, and MPI3D disentanglement datasets, showing state of the art results against previous methods via qualitative traversals in the latent space, as well as quantitative disentanglement metrics. We further qualitatively demonstrate the effectiveness of our model on the real-world CelebA dataset.

As we enter the era of machine learning characterized by an overabundance of data, discovery, organization, and interpretation of the data in an \textit{unsupervised} manner becomes a critical need. One promising approach to this endeavour is the problem of \textit{Disentanglement}, which aims at learning the underlying generative latent factors, called the factors of variation, of the data and encoding them in disjoint latent representations. Recent advances have made efforts to solve this problem for synthetic datasets generated by a fixed set of independent factors of variation. Here, we propose to extend this to real-world datasets with a countable number of factors of variations. We propose a novel framework which augments the latent space of a Variational Autoencoders with a disentangled space and is trained using a Wake-Sleep-inspired two-step algorithm for unsupervised disentanglement. Our network learns to disentangle interpretable, independent factors from the data ``one at a time", and encode it in different dimensions of the disentangled latent space, while making no prior assumptions about the number of factors or their joint distribution. We demonstrate its quantitative and qualitative effectiveness by evaluating the latent representations learned on two synthetic benchmark datasets; DSprites and 3DShapes and on a real datasets CelebA.

Federated learning (FL) is a recently developed area of machine learning, in which the private data of a large number of distributed clients is used to develop a global model under the coordination of a central server without explicitly exposing the data. The standard FL strategy has a number of significant bottlenecks including large communication requirements and high impact on the clients’ resources. Several strategies have been described in the literature trying to address these issues. In this paper, a novel scheme based on the notion of “model growing" is proposed. Initially, the server deploys a small model of low complexity, which is trained to capture the data complexity during the initial set of rounds. When the performance of such a model saturates, the server switches to a larger model with the help of function-preserving transformations. The model complexity increases as more data is processed by the clients, and the overall process continues until the desired performance is achieved. Therefore, the most complex model is broadcast only at the final stage in our approach resulting in substantial reduction in communication cost and client computational requirements. The proposed approach is tested extensively on three standard benchmarks and is shown to achieve substantial reduction in communication and client computation while achieving comparable accuracy when compared to the current most effective strategies.KeywordsCommunication efficiencyFederated learningFunction preserving transformation

As we enter the era of machine learning characterized by an overabundance of data, discovery, organization, and interpretation of the data in an unsupervised manner becomes a critical need. One promising approach to this endeavour is the problem of Disentanglement, which aims at learning the underlying generative latent factors, called the factors of variation, of the data and encoding them in disjoint latent representations. Recent advances have made efforts to solve this problem for synthetic datasets generated by a fixed set of independent factors of variation. Here, we propose to extend this to real-world datasets with a countable number of factors of variations. We propose a novel framework which augments the latent space of a Variational Autoencoders with a disentangled space and is trained using a Wake-Sleep-inspired two-step algorithm for unsupervised disentanglement. Our network learns to disentangle interpretable, independent factors from the data “one at a time”, and encode it in different dimensions of the disentangled latent space, while making no prior assumptions about the number of factors or their joint distribution. We demonstrate its quantitative and qualitative effectiveness by evaluating the latent representations learned on two synthetic benchmark datasets; DSprites and 3DShapes and on a real datasets CelebA.KeywordsDeep learningRepresentation learningUnsupervised disentanglement

Federated learning (FL) is a recently developed area of machine learning, in which the private data of a large number of distributed clients is used to develop a global model under the coordination of a central server without explicitly exposing the data. The standard FL strategy has a number of significant bottlenecks including large communication requirements and high impact on the clients' resources. Several strategies have been described in the literature trying to address these issues. In this paper, a novel scheme based on the notion of "model growing" is proposed. Initially, the server deploys a small model of low complexity, which is trained to capture the data complexity during the initial set of rounds. When the performance of such a model saturates, the server switches to a larger model with the help of function-preserving transformations. The model complexity increases as more data is processed by the clients, and the overall process continues until the desired performance is achieved. Therefore, the most complex model is broadcast only at the final stage in our approach resulting in substantial reduction in communication cost and client computational requirements. The proposed approach is tested extensively on three standard benchmarks and is shown to achieve substantial reduction in communication and client computation while achieving comparable accuracy when compared to the current most effective strategies.

Generating confidence calibrated outputs is of utmost importance for the applications of deep neural networks in safety-critical decision-making systems. The output of a neural network is a probability distribution where the scores are estimated confidences of the input belonging to the corresponding classes, and hence they represent a complete estimate of the output likelihood relative to all classes. In this paper, we propose a novel form of label smoothing to improve confidence calibration. Since different classes are of different intrinsic similarities, more similar classes should result in closer probability values in the final output. This motivates the development of a new smooth label where the label values are based on similarities with the reference class. We adopt different similarity measurements, including those that capture feature-based similarities or semantic similarity. We demonstrate through extensive experiments, on various datasets and network architectures, that our approach consistently outperforms state-of-the-art calibration techniques including uniform label smoothing.

Insights from functional Magnetic Resonance Imaging (fMRI), as well as recordings of large numbers of neurons, reveal that many cognitive, emotional, and motor functions depend on the multivariate interactions of brain signals. To decode brain dynamics, we propose an architecture based on recurrent neural networks to uncover distributed spatiotemporal signatures. We demonstrate the potential of the approach using human fMRI data during movie-watching data and a continuous experimental paradigm. The model was able to learn spatiotemporal patterns that supported 15-way movie-clip classification (∼90%) at the level of brain regions, and binary classification of experimental conditions (∼60%) at the level of voxels. The model was also able to learn individual differences in measures of fluid intelligence and verbal IQ at levels comparable to that of existing techniques. We propose a dimensionality reduction approach that uncovers low-dimensional trajectories and captures essential informational (i.e., classification related) properties of brain dynamics. Finally, saliency maps and lesion analysis were employed to characterize brain-region/voxel importance, and uncovered how dynamic but consistent changes in fMRI activation influenced decoding performance. When applied at the level of voxels, our framework implements a dynamic version of multivariate pattern analysis. Our approach provides a framework for visualizing, analyzing, and discovering dynamic spatially distributed brain representations during naturalistic conditions.