Witness detection in multi-instance regression and its application for age estimation

The huge data resource on the Web provides us with an emerging chance to solve the lack of training sample problem that lasting for years in facial age estimation. We show that the web images assisted age estimation can be modeled into a Multiple Instance Regression (MIR) problem. Different from the traditional Multiple Instance Learning (MIL) problem that deals with the bag-level classification task, we model the age estimation problem as an instance-level task. To this end, it is essential to reveal the latent instance labels from all bags. In this paper, we propose a novel algorithm named Witness Detecting Multi-instance Regression (WDMR) that can find all possible positive instances from training bags and use them to train an instance-level regressor. Considering the connection between neighbor relationship and inter-/intra- class differences among instances, we develop a Supervised Citer k-Nearest Neighbor (SC-kNN) graph and a sparse voting strategy to address these problems within a joint learning framework. Experimental results on synthetic and real-world datasets have verified the advantages of our method compared with other state-of-the-art MIL approaches.

[1]  Rama Chellappa,et al.  Learning Common and Feature-Specific Patterns: A Novel Multiple-Sparse-Representation-Based Tracker , 2018, IEEE Transactions on Image Processing.

[2]  Bingbing Ni,et al.  Web Image and Video Mining Towards Universal and Robust Age Estimator , 2011, IEEE Transactions on Multimedia.

[3]  Annabella Astorino,et al.  A Lagrangian Relaxation Approach for Binary Multiple Instance Classification , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[4]  Brendan J. Frey,et al.  Classifying and segmenting microscopy images with deep multiple instance learning , 2015, Bioinform..

[5]  Zhi-Hua Zhou,et al.  Facial Age Estimation by Learning from Label Distributions , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Nanning Zheng,et al.  Double layer multiple task learning for age estimation with insufficient training samples , 2015, Neurocomputing.

[7]  Andrew Zisserman,et al.  Deep Face Recognition , 2015, BMVC.

[8]  Yun Fu,et al.  Age Synthesis and Estimation via Faces: A Survey , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Ivor W. Tsang,et al.  A Convex Method for Locating Regions of Interest with Multi-instance Learning , 2009, ECML/PKDD.

[10]  Ping Zhong,et al.  Multiple Instance Learning for Multiple Diverse Hyperspectral Target Characterizations , 2020, IEEE Transactions on Neural Networks and Learning Systems.

[11]  Haibin Liao Facial age feature extraction based on deep sparse representation , 2018, Multimedia Tools and Applications.

[12]  Rama Chellappa,et al.  Robust MIL-Based Feature Template Learning for Object Tracking , 2017, AAAI.

[13]  Jianru Xue,et al.  Facial age estimation from web photos using multiple-instance learning , 2014, 2014 IEEE International Conference on Multimedia and Expo (ICME).

[14]  Guoqing Liu,et al.  Key Instance Detection in Multi-Instance Learning , 2012, ACML.

[15]  Cordelia Schmid,et al.  Is that you? Metric learning approaches for face identification , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[16]  Kaihua Zhang,et al.  Real-time visual tracking via online weighted multiple instance learning , 2013, Pattern Recognit..

[17]  Zheng Gao,et al.  Fast compressive tracking with robust example selection based on multiple instance learning in smart and autonomous systems , 2017, Pattern Recognit..

[18]  Pong C. Yuen,et al.  Learning Modality-Consistency Feature Templates: A Robust RGB-Infrared Tracking System , 2019, IEEE Transactions on Industrial Electronics.

[19]  Thomas G. Dietterich,et al.  Solving the Multiple Instance Problem with Axis-Parallel Rectangles , 1997, Artif. Intell..

[20]  Ming-Hsuan Yang,et al.  Robust Object Tracking with Online Multiple Instance Learning , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Jun Wang,et al.  Solving the Multiple-Instance Problem: A Lazy Learning Approach , 2000, ICML.

[22]  Luc Van Gool,et al.  Face Detection without Bells and Whistles , 2014, ECCV.

[23]  Kai Li,et al.  Deep Cost-Sensitive and Order-Preserving Feature Learning for Cross-Population Age Estimation , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[24]  Yueting Zhuang,et al.  Data-Dependent Label Distribution Learning for Age Estimation , 2017, IEEE Transactions on Image Processing.

[25]  Dong Wang,et al.  Multiple-Instance Learning Via Random Walk , 2006, ECML.