The Town Hall meeting is open to all registered attendees, and is an opportunity to connect, ask questions and provide feedback to the ICLR organizers.
Please visit https://chat.iclr.cc/channel/townhall for the discussion that took place during the Town Hall.
Perceiving the 3D World from Images and Video
As humans we take the ability to perceive the dynamic world around us in three dimensions for granted. From an early age we can grasp an object by adapting our fingers to its 3D shape; understand our mother’s feelings by interpreting her facial expressions; or effortlessly navigate through a busy street. All these tasks require some internal 3D representation of shape, deformations, and motion. Building algorithms that can emulate this level of human 3D perception, using as input single images or video sequences taken with a consumer camera, has proved to be an extremely hard task. Machine learning solutions have faced the challenge of the scarcity of 3D annotations, encouraging important advances in weak and self-supervision. In this talk I will describe progress from early optimization-based solutions that captured sequence-specific 3D models with primitive representations of deformation, towards recent and more powerful 3D-aware neural representations that can learn the variation of shapes and textures across a category and be trained from 2D image supervision only. There has been very successful recent commercial uptake of this technology and I will show exciting applications to AI-driven video synthesis.
Is My Dataset Biased?
Is my dataset biased? The answer is likely, yes. In machine learning, “dataset bias” happens when the training data is not representative of future test data. Finite datasets cannot include all variations possible in the real world, so every machine learning dataset is biased in some way. Yet, machine learning progress is traditionally measured by testing on in-distribution data. This obscures the real danger that models will fail on new domains. For example, a pedestrian detector trained on pictures of people in the sidewalk could fail on jaywalkers. A medical classifier could fail on data from a new sensor or hospital. The good news is, we can fight dataset bias with techniques from domain adaptation, semi-supervised learning and generative modeling. I will describe the evolution of efforts to improve domain transfer, their successes and failures, and a vision for the future.
How is Amazon using Representation Learning to innovate on behalf of customers? This panel will feature Amazon Scholars and Visiting Academics including professors from around the world, sharing how they leverage their RL expertise and apply their research at Amazon in new, inventive ways. Moderated by Academic Program Manager, Lindsey Weil, this panel will provide insight into how Amazon is leveraging RL and ways academics can partner with Amazon in this domain. The ICLR community is invited to hear about Academics’ projects, best practices, and their experience collaborating with Amazon.