ARTÍCULO
TITULO

Uncertainty Flow Facilitates Zero-Shot Multi-Label Learning in Affective Facial Analysis

Wenjun Bai    
Changqin Quan and Zhiwei Luo    

Resumen

Featured Application: The proposed Uncertainty Flow framework may benefit the facial analysis with its promised elevation in discriminability in multi-label affective classification tasks. Moreover, this framework also allows the efficient model training and between tasks knowledge transfer. The applications that rely heavily on continuous prediction on emotional valance, e.g., to monitor prisoners? emotional stability in jail, can be directly benefited from our framework. Abstract: To lower the single-label dependency on affective facial analysis, it urges the fruition of multi-label affective learning. The impediment to practical implementation of existing multi-label algorithms pertains to scarcity of scalable multi-label training datasets. To resolve this, an inductive transfer learning based framework, i.e.,Uncertainty Flow, is put forward in this research to allow knowledge transfer from a single labelled emotion recognition task to a multi-label affective recognition task. I.e., the model uncertainty?which can be quantified in Uncertainty Flow?is distilled from a single-label learning task. The distilled model uncertainty ensures the later efficient zero-shot multi-label affective learning. On the theoretical perspective, within our proposed Uncertainty Flow framework, the feasibility of applying weakly informative priors, e.g., uniform and Cauchy prior, is fully explored in this research. More importantly, based on the derived weight uncertainty, three sets of prediction related uncertainty indexes, i.e., soft-max uncertainty, pure uncertainty and uncertainty plus are proposed to produce reliable and accurate multi-label predictions. Validated on our manual annotated evaluation dataset, i.e., the multi-label annotated FER2013, our proposed Uncertainty Flow in multi-label facial expression analysis exhibited superiority to conventional multi-label learning algorithms and multi-label compatible neural networks. The success of our proposed Uncertainty Flow provides a glimpse of future in continuous, uncertain, and multi-label affective computing.

 Artículos similares

       
 
Yang Liu, Yuanyuan Li, Lu Hu     Pág. 571 - 590
This paper examines commuters? departure time and route choices in the morning commute problem when travel time is described as a bounded distributional uncertainty set. The preferences towards risk and ambiguity are distinguished by adopting the ambigui... ver más

 
Yongnan Zhu, Zhaohui Lin, Yong Zhao, Haihong Li, Fan He, Jiaqi Zhai, Lizhen Wang, Qingming Wang     Pág. 1 - 13
The performances of hydrological simulations for the Pearl River Basin in China were analysed using the Coupled Land Surface and Hydrological Model System (CLHMS). Three datasets, including East Asia (EA), high-resolution gauge satellite-merged China Mer... ver más
Revista: Water

 
Usman T. Khan, Caterina Valeo     Pág. 1 - 24
A fuzzy neural network method is proposed to predict minimum daily dissolved oxygen concentration in the Bow River, in Calgary, Canada. Owing to the highly complex and uncertain physical system, a data-driven and fuzzy number based approach is preferred ... ver más
Revista: Water

 
Sean Zeiger, Jason Hubbart     Pág. 1 - 20
Accurate mean areal precipitation (MAP) estimates are essential input forcings for hydrologic models. However, the selection of the most accurate method to estimate MAP can be daunting because there are numerous methods to choose from (e.g., proximate ga... ver más
Revista: Water

 
Khan Garee, Xi Chen, Anming Bao, Yu Wang, Fanhao Meng     Pág. 1 - 20
The Soil andWater Assessment Tool (SWAT) model combined with a temperature index and elevation band algorithm was applied to the Hunza watershed, where snow and glacier-melt are the major contributor to river flow. This study?s uniqueness is its use of a... ver más
Revista: Water