Header logo is de
Vorträge

Robust Discrimination and Generation of Faces using Compact, Disentangled Embeddings

Talk
  • 22 August 2019 • 15:00 16:00
  • Björn Browatzki
  • PS Aquarium

Current solutions to discriminative and generative tasks in computer vision exist separately and often lack interpretability and explainability. Using faces as our application domain, here we present an architecture that is based around two core ideas that address these issues: first, our framework learns an unsupervised, low-dimensional embedding of faces using an adversarial autoencoder that is able to synthesize high-quality face images. Second, a supervised disentanglement splits the low-dimensional embedding vector into four sub-vectors, each of which contains separated information about one of four major face attributes (pose, identity, expression, and style) that can be used both for discriminative tasks and for manipulating all four attributes in an explicit manner. The resulting architecture achieves state-of-the-art image quality, good discrimination and face retrieval results on each of the four attributes, and supports various face editing tasks using a face representation of only 99 dimensions. Finally, we apply the architecture's robust image synthesis capabilities to visually debug label-quality issues in an existing face dataset.

Organizers: Timo Bolkart

  • Prof. Shu Yang
  • 2P04

Geometry is concerned with the properties of configurations of points, lines, and circles, while topology is concerned with space, dimension, and transformation. Geometry is also materials independent and scale invariant. By introducing holes and cuts in 2D sheets, we demonstrate dramatic shape change and super-conformability via expanding or collapsing of the hole arrays without deforming individual lattice units. When choosing the cuts and geometry correctly, we show folding into the third dimension, known as kirigami. The kirigami structures can be rendered pluripotent, that is changing into different 3D structures from the same 2D sheet. We explore their potential applications in energy efficient building facade, super-stretchable and shape conformable energy storage devices and medical devices, as well as bioinspired robotics. Programmable shape-shifting materials can take different physical forms to achieve multifunctionality in a dynamic and controllable manner. Through designs of geometric surface patterns, e.g. microchannels, we program the orientational elasticity in liquid crystal elastomers (LCEs), to direct folding of the 2D sheets into 3D shapes, which can be triggered by heat, light, and electric field. Taking this knowledge of guided inhomogeneous local deformations in LCEs, we then tackle the inverse problem – pre-programming geometry on a flat sheet to take an arbitrary desired 3D shape. Lastly, I will show the prospective of taking geometry to create smart fabrics and tendon-like filaments for soft robotic applications.


  • Adriane Boyd
  • PS-Aquarium

We develop a grammatical error correction system for German using a small gold corpus augmented with edits extracted from Wikipedia revision history. We extend the automatic error annotation tool ERRANT (Bryant et al., 2017) for German and use it to analyze both gold corrections and Wikipedia edits (Grundkiewicz and Junczys-Dowmunt, 2014) in order to select as additional training data Wikipedia edits containing grammatical corrections similar to those in the gold corpus. Using a neural machine translation approach (Chollampatt and Ng, 2018), we evaluate the contribution of Wikipedia edits and find that carefully selected Wikipedia edits increase performance by over 5%.

Organizers: Jean-Claude Passy


  • Dr Antonia Tzemanaki
  • PS-Aquarium

Over the past century, abdominal surgery has seen a rapid transition from open procedures to less invasive methods such as laparoscopy and robot-assisted minimally invasive surgery (R-A MIS), as they involve reduced blood loss, postoperative morbidity and length of hospital stay. Furthermore, R-A MIS has offered refined accuracy and more ergonomic instruments for surgeons, further minimising trauma to the patient. However, training surgeons in MIS procedures is becoming increasingly long and arduous, while commercially available robotic systems adopt a design similar to conventional laparoscopic instruments with limited novelty. Do these systems satisfy their users? What is the role and importance of haptics? Taking into account the input of end-users as well as examining the high intricacy and dexterity of the human hand can help to bridge the gap between R-A MIS and open surgery. By adopting designs inspired by the human hand, robotic tele-operated systems could become more accessible not only in the surgical domain but, beyond, in areas that benefit from user-centred design such as stroke rehabilitation, as well as in areas where safety issues prevent use of autonomous robots, such as assistive technologies and nuclear industry.

Organizers: Dimitrios Tzionas


  • Yasemin Vardar
  • 2P4 in Heisenbergstr. 3

Sign-Up! is a career-building program for female post-docs in the Max Planck Society. This program aims to prepare post-doctoral researchers for their future scientific careers by several interactive training sessions and networking activities. As a selected member of this program, I will summarize the workshops that I participated in this year. My talk will cover topics about success factors in scientific careers, career planning, professional communication and leadership, self-presentation, and research funding.

Organizers: Katherine J. Kuchenbecker


Anthropomorphism in Surgical Robotics and Wearable Technologies

IS Colloquium
  • 03 June 2019 • 11:00 12:00
  • Dr Antonia Tzemanaki
  • MPI-IS Stuttgart, Heisenbergstr. 3, Room 2P4

Over the past century, abdominal surgery has seen a rapid transition from open procedures to less invasive methods such as laparoscopy and robot-assisted minimally invasive surgery (R-A MIS), as they involve reduced blood loss, postoperative morbidity and length of hospital stay. Furthermore, R-A MIS has offered refined accuracy and more ergonomic instruments for surgeons, further minimising trauma to the patient. However, training surgeons in MIS procedures is becoming increasingly long and arduous, while commercially available robotic systems adopt a design similar to conventional laparoscopic instruments with limited novelty. Do these systems satisfy their users? What is the role and importance of haptics? Taking into account the input of end-users as well as examining the high intricacy and dexterity of the human hand can help to bridge the gap between R-A MIS and open surgery. By adopting designs inspired by the human hand, robotic tele-operated systems could become more accessible not only in the surgical domain but, beyond, in areas that benefit from user-centred design such as stroke rehabilitation, as well as in areas where safety issues prevent use of autonomous robots, such as assistive technologies and nuclear industry.

Organizers: Katherine J. Kuchenbecker


Human Factors Research in Minimally Invasive Surgery

IS Colloquium
  • 23 May 2019 • 11:00 12:00
  • Caroline G. L. Cao, Ph.D.
  • MPI-IS Stuttgart, Heisenbergstr. 3, Room 2P4

Health care is probably the last remaining unsafe critical system. A large proportion of reported medical errors occur in the hospital operating room (OR), a highly complex sociotechnical environment. As technology is being introduced into the OR faster than surgeons can learn to use them, surgical errors result from the unfamiliar instrumentation, increased motoric, perceptual and cognitive demands on the surgeons, as well as the lack of adequate training. Effective technology design for minimally invasive surgery requires an understanding of the system constraints of remote surgery, and the complex interaction between humans and technology in the OR. This talk will describe research activities in the Ergonomics in Remote Environments Laboratory at Wright State University, which address some of these human factors issues.

Organizers: Katherine J. Kuchenbecker


  • Jinlong Yang
  • PS Aquarium

In the past few years, significant progress has been made on shape modeling of human body, face, and hands. Yet clothing shape is currently not well presented. Modeling clothing using physics-based simulation can sometimes involve tedious manual work and heavy computation. Therefore, a data-driven learning approach has emerged in the community. In this talk, I will present a stream of work that targeted to learn the shape of clothed human from captured data. It involves 3D body estimation, clothing surface registration and clothing deformation modeling. I will conclude this talk by outlining the current challenges and some promising research directions in this field.

Organizers: Timo Bolkart


  • Dr. Urartu Şeker
  • 2P04

Programming cellular devices to deliver proteins or small molecules using synthetic genetic regulation can be employed in many areas such as biomedicine, living therapeutics, living materials and many others. A biological device composed of a cellular sensor coupled with a programmed protein delivery system can lead the formation of a synthetic system that can sense the environmental inputs, carry out calculations and create an output. Using this approach, we have built cellular devices those can sense environmental signals and creates an output in the form of protein secretion. In this talk I will mention about a self-actuated cellular protein delivery system which utilizes logic gate based, and state-machine based operations for sequential protein delivery. Also, I will mention about our recent studies to create synthetic genetic circuits those rely on a sense-response approach. These will include a cellular device for a whole cell biocatalyst and another device for nanomaterial templating.


  • Marilyn Keller
  • Aquarium

Since the release of the Kinect, RGB-D cameras have been used in several consumer devices, including smartphones. In this talk, I will present two challenging uses of this technology. With multiple RGB-D cameras, it is possible to reconstruct a 3D scene and visualize it from any point of view. In the first part of the talk, I will show how such a scene can be streamed and rendered as a point cloud in a compelling way and its appearance improved by the use of external cinema cameras. In the second part of the talk, I will present my work on how an RGB-D camera can be used for enabling real-walking in virtual reality by making the user aware of the surrounding obstacles. I present a pipeline to create an occupancy map from a point cloud on the fly on a mobile phone used as a virtual reality headset. This occupancy map can then be used to prevent the user from hitting physical obstacles when walking in the virtual scene.

Organizers: Sergi Pujades


Unsupervised Learning: Passiv and Active

Talk
  • 11 April 2019 • 16:30 17:30
  • Professor Jürgen Schmidhuber
  • MPI IS lecture hall N0.002

I’ll start with a concept of 1990 that has become popular: unsupervised learning without a teacher through two adversarial neural networks (NNs) that duel in a minimax game, where one NN minimizes the objective function maximized by the other. The first NN generates data through its output actions, the second NN predicts the data. The second NN minimizes its error, thus becoming a better predictor. But it is a zero sum game: the first NN tries to find actions that maximize the error of the second NN. The system exhibits what I called “artificial curiosity” because the first NN is motivated to invent actions that yield data that the second NN still finds surprising, until the data becomes familiar and eventually boring. A similar adversarial zero sum game was used for another unsupervised method called "predictability minimization," where two NNs fight each other to discover a disentangled code of the incoming data (since 1991), remarkably similar to codes found in biological brains. I’ll also discuss passive unsupervised learning through predictive coding of an agent’s observation stream (since 1991) to overcome the fundamental deep learning problem through data compression. I’ll offer thoughts as to why most current commercial applications don’t use unsupervised learning, and whether that will change in the future.

Organizers: Bernhard Schölkopf