Energy-Aware NECO for Single-Pass Pixel-wise Out-of-Distribution Detection in Semantic Segmentation 事件

Energy-Aware NECO for Single-Pass Pixel-wise Out-of-Distribution Detection in Semantic Segmentation arXiv:2605.29773v1 Announce Type: new Abstract: Reliable semantic segmentation for mobile robots requires both accurate dense prediction and robust uncertainty estimation under distribution shift. Strong uncertainty baselines such as Monte Carlo Dropout often require repeated stochastic forward passes and are difficult to deploy on edge platforms. We propose Energy-Aware NECO, a single-pass pix