Next-generation deep learning based on simulators and synthetic data
Deep learning (DL) is being successfully applied across multiple domains, yet these models
learn in a most artificial way: they require large quantities of labeled data to grasp even …
learn in a most artificial way: they require large quantities of labeled data to grasp even …
Incorporating physics into data-driven computer vision
Many computer vision techniques infer properties of our physical world from images.
Although images are formed through the physics of light and mechanics, computer vision …
Although images are formed through the physics of light and mechanics, computer vision …
Generalizing to unseen domains: A survey on domain generalization
Machine learning systems generally assume that the training and testing distributions are
the same. To this end, a key requirement is to develop models that can generalize to unseen …
the same. To this end, a key requirement is to develop models that can generalize to unseen …
Learning to generate novel domains for domain generalization
This paper focuses on domain generalization (DG), the task of learning from multiple source
domains a model that generalizes well to unseen domains. A main challenge for DG is that …
domains a model that generalizes well to unseen domains. A main challenge for DG is that …
A simple feature augmentation for domain generalization
The topical domain generalization (DG) problem asks trained models to perform well on an
unseen target domain with different data statistics from the source training domains. In …
unseen target domain with different data statistics from the source training domains. In …
Fsdr: Frequency space domain randomization for domain generalization
Abstract Domain generalization aims to learn a generalizable model from aknown'source
domain for variousunknown'target domains. It has been studied widely by domain …
domain for variousunknown'target domains. It has been studied widely by domain …
Parameter-free online test-time adaptation
Training state-of-the-art vision models has become prohibitively expensive for researchers
and practitioners. For the sake of accessibility and resource reuse, it is important to focus on …
and practitioners. For the sake of accessibility and resource reuse, it is important to focus on …
A survey on safety-critical driving scenario generation—A methodological perspective
Autonomous driving systems have witnessed significant development during the past years
thanks to the advance in machine learning-enabled sensing and decision-making …
thanks to the advance in machine learning-enabled sensing and decision-making …
Domain randomization and pyramid consistency: Simulation-to-real generalization without accessing target domain data
We propose to harness the potential of simulation for semantic segmentation of real-world
self-driving scenes in a domain generalization fashion. The segmentation network is trained …
self-driving scenes in a domain generalization fashion. The segmentation network is trained …
MIME: Human-aware 3D scene generation
H Yi, CHP Huang, S Tripathi, L Hering… - Proceedings of the …, 2023 - openaccess.thecvf.com
Generating realistic 3D worlds occupied by moving humans has many applications in
games, architecture, and synthetic data creation. But generating such scenes is expensive …
games, architecture, and synthetic data creation. But generating such scenes is expensive …