Journal ArticleDOI
Relative Attribute SVM+ Learning for Age Estimation
Reads0
Chats0
TLDR
This work defines relative attributes for support vector machine (SVM+) as relative attribute SVM+ (raSVM+), in which the privileged information enables separation of outliers from inliers at the training stage and effectively manipulates slack variables and age determination errors during model training, and thus guides the trained predictor toward a generalizable solution.Abstract:
When estimating age, human experts can provide privileged information that encodes the facial attributes of aging, such as smoothness, face shape, face acne, wrinkles, and bags under-eyes. In automatic age estimation, privileged information is unavailable to test images. To overcome this problem, we hypothesize that asymmetric information can be explored and exploited to improve the generalizability of the trained model. Using the learning using privileged information (LUPI) framework, we tested this hypothesis by carefully defining relative attributes for support vector machine (SVM+) to improve the performance of age estimation. We term this specific setting as relative attribute SVM+ (raSVM+), in which the privileged information enables separation of outliers from inliers at the training stage and effectively manipulates slack variables and age determination errors during model training, and thus guides the trained predictor toward a generalizable solution. Experimentally, the superiority of raSVM+ was confirmed by comparing it with state-of-the-art algorithms on the face and gesture recognition research network (FG-NET) and craniofacial longitudinal morphological face aging databases. raSVM+ is a promising development that improves age estimation, with the mean absolute error reaching 4.07 on FG-NET.read more
Citations
More filters
Journal ArticleDOI
Age from Faces in the Deep Learning Revolution
TL;DR: This paper provides an analysis of the deep methods proposed in the last six years from different points of view: the network architecture together with the learning procedure, the used datasets, data preprocessing and augmentation, and the exploitation of additional data coming from gender, race and face expression.
Proceedings ArticleDOI
Curriculum Learning for Multi-task Classification of Visual Attributes
TL;DR: In this paper, the authors combine the advantages of both multi-task and curriculum learning in a visual attribute classification framework, where individual tasks are grouped based on their correlation so that two groups of strongly and weakly correlated tasks are formed.
Journal ArticleDOI
Random Forest Classifier for Zero-Shot Learning Based on Relative Attribute
TL;DR: Experiments on Outdoor Scene Recognition, Pub Fig, and Shoes data sets show that the proposed method is superior to several state-of-the-art methods in terms of classification capability for zero-shot learning problems.
Journal ArticleDOI
Human Facial Age Estimation by Cost-Sensitive Label Ranking and Trace Norm Regularization
TL;DR: This work proposes a novel approach that combines the strength of cost-sensitive label ranking methods with the power of low-rank matrix recovery theories for facial age estimation, and extends the trace norm regularization from a finite dimensional space to an infinite dimensional space.
Journal ArticleDOI
Modeling of facial aging and kinship: A survey
TL;DR: In this paper, the authors provide an up-to-date, complete list of available annotated datasets and an in-depth analysis of geometric, hand-crafted, and learned facial representations that are used for facial aging and kinship characterization.
References
More filters
Journal ArticleDOI
Distinctive Image Features from Scale-Invariant Keypoints
TL;DR: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
Fast training of support vector machines using sequential minimal optimization, advances in kernel methods
TL;DR: SMO breaks this large quadratic programming problem into a series of smallest possible QP problems, which avoids using a time-consuming numerical QP optimization as an inner loop and hence SMO is fastest for linear SVMs and sparse data sets.
Book
Fast training of support vector machines using sequential minimal optimization
TL;DR: In this article, the authors proposed a new algorithm for training Support Vector Machines (SVM) called SMO (Sequential Minimal Optimization), which breaks this large QP problem into a series of smallest possible QP problems.
Journal ArticleDOI
Smooth minimization of non-smooth functions
TL;DR: A new approach for constructing efficient schemes for non-smooth convex optimization is proposed, based on a special smoothing technique, which can be applied to functions with explicit max-structure, and can be considered as an alternative to black-box minimization.
Proceedings ArticleDOI
Training linear SVMs in linear time
TL;DR: A Cutting Plane Algorithm for training linear SVMs that provably has training time 0(s,n) for classification problems and o(sn log (n)) for ordinal regression problems and several orders of magnitude faster than decomposition methods like svm light for large datasets.