When deploying a robot to new task, one often has train it detect novel objects, which is time-consuming and labor-intensive. We present TAILOR -- method system for object registration with active incremental learning. instructed by human teacher register an object, able automatically select viewpoints capture informative images actively exploring viewpoints, employs fast learning algorithm lea...

Deep neural networks use skip connections to improve training convergence. However, these are costly in hardware, requiring extra buffers and increasing on- off-chip memory utilization bandwidth requirements. In this paper, we show that can be optimized for hardware when tackled with a hardware-software codesign approach. We argue while network’s needed the network learn, they later removed or ...