ICAI: The Labs – AI for Travel in the NL

In March 2022, ICAI: The Labs is focused on AI for Travel in the Netherlands. The Atlas lab and the Mercury Machine Learning Lab each present their work and discuss challenges and developments made in this field.

Atlas Lab is a collaboration between ‘location technology specialist’ TomTom (TOM2) and the University of Amsterdam (UvA). The public-private research lab focuses on using Artificial Intelligence (AI) for developing advanced, highly accurate, and safe high definition (HD) maps for self-driving vehicles.

The Mercury Machine Learning Lab (MML Lab) is a collaboration between the University of Amsterdam, Delft University of Technology, and Booking.com. The lab focuses on the development and applications of artificial intelligence to the specific domain of online travel booking and recommendation service systems.

Program

12.00 (noon): Opening

12:05: Introduction of the Atlas Lab by Martin Oswald (UvA)

12:10: Duy-Kien Nguyen (UvA) presents “BoxeR: Box-Attention for 2D and 3D Transformers”

12.25: Onno Zoeter (Booking.com) presents Introduction of the MML lab and its proposed research agenda

12.45: Discussion what’s next in AI for Travel in NL

13.00: End

Abstracts

“The Mercury Machine Learning Lab, Learning from Controlled Sources”

The classic supervised learning problem that is taught in machine learning courses and is the subject of many machine learning competitions, is often too narrow to reflect the problems that we face in practice. Historical datasets typically reflect a combination of a source of randomness (for example customers making browsing and buying decisions) and a controlling mechanism such as a ranker or highlighting heuristics (badges, promotions, etc.). Or there might be a selection mechanism (such as the decision to not accept transactions with high fraud risk) that influences the training data. A straightforward regression approach would not be able to disentangle the influence of the controller and phenomenon under study. As a result it risks making incorrect predictions as the controller is changed.

In practice however, such problems are typically treated as a classic regression problem in a first iteration and attempts to identify and correct for these complications come as afterthoughts or are not undertaken at all. Ideally there is a rigorous and flexible formalism that captures the correct framing of the problem from the very start, accompanied by a set of practical algorithms that work well in practice for each of the identified cases.

This research objective is the main goal of the Mercury Machine Learning Lab, a collaboration between the University of Amsterdam, the Technical University of Delft and Booking.com. It brings together the fields of information retrieval, causality and reinforcement learning where the topic is studied under the names of off-line evaluation, transferability and s-recoverability and off-policy learning respectively.

This presentation will sketch the problem and discusses early results.

“BoxeR: Box-Attention for 2D and 3D Transformers”

We propose a simple attention mechanism, we call Box-Attention. It enables spatial interaction between grid features, as sampled from boxes of interest, and im- proves the learning capability of transformers for several vision tasks. Specifically, we present BoxeR, short for Box Transformer, which attends to a set of boxes by predicting their transformation from a reference window on an input feature map. The BoxeR computes attention weights on these boxes by considering its grid structure. Notably, BoxeR-2D naturally reasons about box information within its attention module, making it suitable for end-to-end instance detection and segmentation tasks. By learning invariance to rotation in the box-attention module, BoxeR-3D is capable of generating discriminative information from a bird-eye-view plane for 3D end-to-end object detection. Our experiments demonstrate that the proposed BoxeR-2D achieves better results on COCO detection, and reaches comparable performance with well-established and highly-optimized Mask R-CNN on COCO instance segmentation. BoxeR-3D already obtains a compelling performance for the vehicle category of Waymo Open, without any class-specific optimization.