Profile of TAs
Sebastian Gerard
- Brief Bio: PhD student at RPL working on self-supervised learning on satellite images
- Deep learning software packages:
- Pytorch
- Pytorch Lightning
- wandb
- Deep learning methodologies, architectures and application fields:
- Self-supervised learning for images
- Segmentation
- Satellite images
Yiping Xie
- Brief Bio: PhD student in RPL and WASP, working on learning the representations of underwater perception for navigation.
- Deep learning software packages:
- Pytorch
- Deep learning methodologies, architectures and application fields:
- Generally discriminative models and generative models (VAEs, GANs)
- Computer Visions applications: depth estimation and etc.
- Computer Graphics: differentiable rendering, neural representation
- Sidescan Sonar images
Alfredo Reichlin
- Brief Bio: PhD student at RPL working mainly on Imitation Learning, Offline Reinforcement Learning and Meta Learning for robotic manipulation
- Deep learning software packages:
- Pytorch
- Deep learning methodologies, architectures and application fields:
- representation learning from images
- few-shot adaptation
- mostly CNN
- some Graph Neural Networks
- some generative models (VAEs, GANs)
Heng Fang
- Brief Bio: Ph.D. student at RPL working on change detection and uncertainty estimation on satellite images
- Deep learning software packages:
- Pytorch
- Deep learning methodologies, architectures and application fields:
- Computer vision applications in satellite imagery and biomedical scenarios
- Segmentation, change detection, and uncertainty estimation
I was a student of this course in 2019, feel free to contact me if you have any proposal ideas for the projects.
Li Ling
- Brief Bio: PhD student in RPL, working on sonar-based perception for underwater navigation.
- Deep learning software packages:
- Pytorch
- Deep learning methodologies, architectures and application fields:
- Keypoint detection, description and matching for images
- Sidescan Sonar images
- Interested in contrastive representation learning for images
Lennart Alexander van der Goten
- Brief Bio: Third year PhD student at CST (SciLifeLab) working on domain adaptation & anonymization on biomedical data (CT, MRI etc.)
- Deep learning software packages:
- Pytorch
- TensorFlow
- Deep learning methodologies, architectures and application fields:
- Generative Adversarial Networks
- Variational Autoencoders
- Large-Scale & Distributed Deep Learning
- DL on volumetric data
Ci Li
- Brief Bio: PhD student at RPL working on computer vision and 3D reconstruction on animals from monocular images.
- Deep learning software packages:
- Pytorch
- Deep learning methodologies, architectures and application fields:
- Computer vision applications in pose estimation and motion pattern recognition
- Segmentation, keypoint detections
Marco Moletta
- Brief Bio: PhD student working on representation learning for robotic manipulation of deformable objects, with focus on dynamics prediction and graph representations.
- Deep learning software packages:
- Pytorch
- Deep learning methodologies, architectures and application fields:
- Graph neural networks
- Convolutional neural networks
- Self supervised learning from image and meshes
- Robotic manipulation
Marcel Büsching
- Brief Bio: PhD student at RPL with focus on scene representation, scene reconstruction and neural rendering / novel view generation for dynamic scenes.
- Deep learning software packages:
- PyTorch
- TensorFlow 2
- (jax)
- Deep learning methodologies, architectures and application fields:
- Transformers
- Convolutional Networks
- Undersupervised Learning: SimCLR, FixMatch
- Generative Models: VAE, (Diffusion Models)
- Computer Vision: Scene Reconstruction, Novel View Generation
- Neural Radiance Fields (NeRF)
Shutong Jin
- Brief Bio: PhD student at RPL with a focus on machine learning-based methodologies for robotic manipulation with a focus on large-scale cloud-based robotic systems
- Deep learning software packages:
- PyTorch
- Deep learning methodologies, architectures and application fields:
- Transformers
- Convolutional Neural Network
- Robotic manipulation, object detection and classification