Machine learning models are increasingly being deployed in real-world contexts. However, systematic studies on their transferability to specific and critical applications are underrepresented in the research literature. An important example is visual anomaly detection (V AD) for robotic power line inspection.

We investigated DNNs as encoding models of visual areas V1, V2, V4, and IT. We examined 32 visual deep neural networks.

In these systems, there are two sides: queues (agents) on one side and servers (arms) on the other.

However, these results can be too general to be applicable to natural data distributions. Indeed, humans are quite robust for tasks involving vision.

We introduce Stanford-ORB, a new real-world 3D Object inverse Rendering Benchmark.