Abstract: Deep object detectors suffer from the gradient contribution imbalance during training. In this paper, we point out that such imbalance can be ascribed to the imbalance in example attributes, ...

Abstract: Typically, object detection methods for autonomous driving that rely on supervised learning make the assumption of a consistent feature distribution between the training and testing data, ...

This project aims to develop an object detection system for architectural floor plans using the YOLOv8 model. The system was trained to detect various elements commonly found in floor plans, such as ...

RF-DETR is a real-time transformer architecture for object detection, instance segmentation, and keypoint detection (preview) developed by Roboflow. Built on a DINOv2 vision transformer backbone, ...

ZERO, Superb AI's proprietary Vision Foundation Model, takes first place overall in the CVPR 2026 Foundational Few-Shot ...

Researchers have designed and built the first 3D device that can make objects invisible to heat, an advance that could ...

A camera watching a doorway and a metal detector at that doorway may both support security, but they ask different questions.

Flock cameras are everywhere - even in my small town, quietly using AI to identify your car and surveil your movements. But ...

In the United States alone, more than 150 million people play video games for at least three hours every week, while there ...

A 3D-printed thermal cloak protects objects from detection by infrared cameras. The object inside is also protected from heat ...

We believe that artificially generated content will have a measurably detrimental impact on the pursuit of facts and hence ...

Norwegian scientists have unveiled a new method for tracking silently moving objects, including ships and whales, using fiber ...