However, neither object labels (e.g. "car") nor pose labels (e.g., frontal view) are provided. This mimics robotic vision where the robot pans a camera as it moves around the environment.

Facebook-owner Meta META-Q published an artificial intelligence model on Wednesday that can pick out individual objects from within an image, along with a dataset of image annotations that it said ...

At the most basic level—identifying an object that was unobstructed and in its normal position—both the rats and the AI nailed it. In that case, the AI model only needed to use its first layer.

The concept includes vibration-based GPS navigation, ultrasonic proximity sensors and a camera that can use artificial intelligence to identify objects and faces.

These results highlight dogs’ reliance on different sensory modalities, similar to humans only to some extent, when identifying and generalizing objects.