Confnet: Predict with Confidence
- Resource Type
- Conference
- Authors
- Wan, Sheng; Wu, Tung-Yu; Wong, Wing H.; Lee, Chen-Yi
- Source
- 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Acoustics, Speech and Signal Processing (ICASSP), 2018 IEEE International Conference on. :2921-2925 Apr, 2018
- Subject
- Signal Processing and Analysis
Predictive models
Entropy
Training
Computational modeling
Computational efficiency
Error analysis
Task analysis
Convolutional Neural Network
Deep Learning
Confidence score
Model Cascade
- Language
- ISSN
- 2379-190X
In this paper, we propose Confidence Network (ConfNet) which not only makes predictions on input images but also generates a confidence score that estimates the probability of correctness of each prediction. Furthermore, Confidence Loss is proposed to make ConfNet automatically learn confidence scores in the training phase. The experiments on two public datasets show that the confidence scores generated by ConfNet are highly correlated with the model accuracy and outperforms two related methods. When stacking two ConfNets in a cascade structure, 3.8x computational cost can be saved compared to the single state-of-the-art model with only 0.1 % increase of error rate.