New physics-based machine-learning method speeds search for 2D quantum materials

Researchers at The University of Manchester have developed a new computational approach to help identify two-dimensional ...

Learning to identify new objects reshapes parts of the brain, research finds

The wiring and rewiring of the brain never ends. Neural pathways are constantly being reshaped as we interact with the world ...
IEEE

Explainable Federated Learning-Based Secure and Transparent Object Detection Model for Autonomous Vehicles

Abstract: Intelligent Transportation Systems (ITS) and autonomous vehicles (AVs) are two fast-moving research fields. Understanding the surroundings and acting quickly is essential for AV control, ...
IEEE

Online Decoupled Distillation Based on Prototype Contrastive Learning for Lightweight Underwater Object Detection Models

Abstract: Underwater object detection tasks face significant challenges due to the complexity of aquatic environments and underwater conditions, coupled with the limited computational resources of ...
GitHub

[ICCV2025] CleanPose: Category-Level Object Pose Estimation via Causal Learning and Knowledge Distillation

Official implementation of our CleanPose, the first solution to mitigate the confoundering effect in category-level pose estimation via causal learning and knowledge distillation. You can generate the ...