An Neural Network Framework of Self-Learning Uncertainty

Hanqing Sun^* and Yanwei Pang

Author Affiliations

School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China

show less

DOI: 10.3788/AOS201838.0620002 Cite this Article Set citation alerts

Hanqing Sun, Yanwei Pang. An Neural Network Framework of Self-Learning Uncertainty[J]. Acta Optica Sinica, 2018, 38(6): 0620002 Copy Citation Text

show less

Fig. 1. Architecture of ULNN

Fig. 2. (a) Input data construction procedure of ULNN-rep; (b) input data construction procedure of ULNN-aug

Fig. 3. Components of an UL layer

Fig. 4. Curves of uncertainty learning with different βs (on CIFAR-10, vertical-axis is a logarithmic coordinate)

Fig. 5. Curves of UL (CIFAR-10)

Table 1. Comparison between ULNN-rep and ULNN-aug

Table 2. Impact of input repetition number nu

Table 3. Impact of UL weight β

Table 4. Impact of Dropout on ULNN-aug

Table 5. Comparison of validation result with original training parameters in DenseNet

	Accuracy	mIoU	Uncertainty
Bayesian SegNet	85.9%	51.4%	452.7
ULNN SegNet	87.1%	52.0%	50.63

Table 6. Semantic segmentation results of ULNN SegNet on CamVid

Hanqing Sun, Yanwei Pang. An Neural Network Framework of Self-Learning Uncertainty[J]. Acta Optica Sinica, 2018, 38(6): 0620002

Download Citation