Dimitris N. Metaxas

[intermediate/advanced] Model-based, Explainable, Semisupervised and Unsupervised Machine Learning for Dynamic Analytics in Computer Vision and Medical Image Analysis

Summary

This course will present machine learning methods (supervised, semisupervised and unsupervised) with emphasis on explainability and use of constraints to improve understandability by humans as well as to address abstractions for dynamic analytics in challenging Computer Vision and Medical Image Analysis problems.

Syllabus

• Generative Adversarial Networks
• Overview of Open Problems in Computer Vision and Medical Image Analysis
• Development and use of Machine Learning Methods for Vision and Medical Image Analysis
• Multimodal Input for Improved Analytics, e.g. Language and Vision
• Explainable Machine Learning Methods, Supervised and Unsupervised Methods

References

Han, L., Musunuri, S.H., Min, M.R., Gao, R., Tian, Y. and Metaxas, D., “AE-StyleGAN: Improved Training of Style-Based Auto-Encoders”. In IEEE Winter Conf. on Applications of Computer Vision (WACV), 2022.

Wang, L., Bai, C., Bolonkin, M., Burgoon, J.K., Dunbar, N.E., Subrahmanian, V.S. and Metaxas, D., “Attention-based facial behavior analytics in social communication”. In Detecting Trust and Deception in Group Interaction (pp. 123-137). Springer, Cham, 2021.

Stathopoulos, A., Han, L., Dunbar, N., Burgoon, J.K. and Metaxas, D., “Deception Detection in Videos Using Robust Facial Features”. In Proceedings of the Future Technologies Conference (FTC), 2020.

Zhao, L., Zhang, Z., Chen, T., Metaxas, D. and Zhang, H., “Improved Transformer for High-Resolution GANs”. In Advances in Neural Information Processing Systems (NeurIPS), 2021.

Zhao, L., Wang, Y., Zhao, J., Yuan, L., Sun, J.J., Schroff, F., Adam, H., Peng, X., Metaxas, D. and Liu, T., 2021. Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021.

Metaxas, D.N., Zhao, L. and Peng, X., “Disentangled Representation Learning and Its Application to Face Analytics”. In Deep Learning-Based Face Analytics (pp. 45-72). Springer, Cham, 2021.

Daniels, Z. A., & Metaxas, D. N. (2019, April). Exploiting Visual and Report-Based Information for Chest X-Ray Analysis by Jointly Learning Visual Classifiers and Topic Models. In IEEE International Symposium on Biomedical Imaging (ISBI) (pp. 1270-1274).

Han Zhang, Tao Xu, Hongsheng Li, Shaoting Zhang, Xiaogang Wang, Xiaolei Huang, Dimitris Metaxas. Stackgan: Text to photo-realistic image synthesis with stacked generative adversarial networks. IEEE International Conference on Computer Vision (ICCV), 5907-5915, 2017.

Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio. Generative Adversarial Networks, NeurIPS, 2014.

Pre-requisites

Linear Algebra, Probability and Statistics. Basics of Deep Machine Learning Methods (CNNs, RNNs, UNets, Gradient Descent, Optimization). Some familiarity with Computer Vision and Medical Image Analysis

Short bio

Dimitris Metaxas is a Distinguished Professor in the Computer and Information Sciences Department at Rutgers University. He is directing the Center for Computational Biomedicine, Imaging and Modeling (CBIM) and the NSF University-Industry Collaboration Center CARTA with emphasis on real time and scalable data analytics, AI and machine learning methods with applications to computational biomedicine and computer vision. Dr. Metaxas has been conducting research towards the development of methods and technology upon which AI, machine learning, computer vision, medical image analysis, and computer graphics can advance synergistically. In computer vision, new AI and machine learning methods have been developed for understandable machine learning, real time data analytics, dynamic data driven application systems, 3D human motion analysis, human behaviors and intent recognition, scene understanding and segmentation, surveillance, object recognition, sparsity and biometrics in the wild. In medical and biological image analysis new AI, Machine Learning and model-based methods have been developed for material modeling and shape estimation of internal body parts (e.g., lungs) from MRI, SPAMM and CT data, a pioneering framework for cardiac motion analysis from MRI and CT and for linking the anatomical and physiological models of the human body, cancer diagnosis, histopathology, cell tracking, cell type analysis. Dr. Metaxas has published over 700 research articles in these areas and has graduated over 60 PhD students, who occupy prestigious academic and industry positions. The above research has been funded by AFOSR, ARO, DARPA, HSARPA, NIH, NSF, and the ONR. He is a Fellow of the American Institute of Medical and Biological Engineers, a Fellow of IEEE and a Fellow of the MICCAI Society.