Traditional machine learning paradigms are based on the assumption that both training and
test data follow the same statistical pattern, which is mathematically referred to as …

Abstract Invariant Risk Minimization (IRM) is an emerging invariant feature extracting
technique to help generalization with distributional shift. However, we find that there exists a …

Practical object detection application can lose its effectiveness on image inputs with natural
distribution shifts. This problem leads the research community to pay more attention on the …

Abstract When deploying the Unmanned Aerial Vehicles object detection (UAV-OD) network
to complex and unseen real-world scenarios, the generalization ability is usually reduced …

Contemporary LiDAR-based 3D object detection methods mostly focus on single-domain
learning or cross-domain adaptive learning. However, for autonomous driving systems …

Multimedia recommendation involves personalized ranking tasks, where multimedia content
is usually represented using a generic encoder. However, these generic representations …

Recognition of occluded objects in unseen and unstructured indoor environments is a
challenging problem for mobile robots. To address this challenge, we propose a new …

Supervised 3D Object Detection models have been displaying increasingly better
performance in single-domain cases where the training data comes from the same …

NICO challenge of out-of-distribution (OOD) generalization for image recognition features
two tracks: common context generalization and hybrid context generalization, based on a …

Improving model's generalizability against domain shifts is crucial, especially for safety-
critical applications such as autonomous driving. Real-world domain styles can vary …