In contrast to classic supervised learning methods that demand pre-defined class labels, pairwise encoding or side-information encoding merely requires pairwise similarity information to drive feature learning, which ...
详细信息
ISBN:
(纸本)9781509061679
In contrast to classic supervised learning methods that demand pre-defined class labels, pairwise encoding or side-information encoding merely requires pairwise similarity information to drive feature learning, which makes it very appealing for many fundamental tasks such as dimensionality reduction and semi-supervised learning. In this paper, we present a novel bimarginal pairwise encoding model, along with deepautoencoder, to learn nonlinear embedding for the aforementioned tasks. The new method learns powerful features that preserve critical pairwise information in a semi-supervised manner. It has achieved better performance on the well-known yet hard to make improvement benchmark MINIST compared with other methods in the same category, i.e. autoencoder [4], Invariant Mapping for Dimensionality Reduction [1], Neighborhood Component Analysis [3], and Fixed Bi-Margin Pairwise Encoding [11].
Facial landmark detection is an important issue in a face recognition system. However, human faces in wild conditions often present large variations in shape due to different poses, occlusions or expressions, which ma...
详细信息
ISBN:
(纸本)9781479983391
Facial landmark detection is an important issue in a face recognition system. However, human faces in wild conditions often present large variations in shape due to different poses, occlusions or expressions, which makes it a difficult task. Instead of learning the same map for all images, we propose a Pose-Induced auto-encoder Networks (PIAN) approach which uses different pose-induced networks for landmark estimation under different pose conditions. Firstly, we build a network to simultaneously get the initial landmark and pose estimation. Then, different networks which are induced by the estimated pose are built for local search where a component-based searching method is explored. By using the pose inducing strategy, the initial estimation is reliable and it helps reduce the variations in local patches. This makes the component-based search feasible and more accurate than previous searching methods. Experiments show that our method outperforms the state-of-the-art algorithms especially in terms of fine estimation of landmarks.
Facial landmark detection is an important issue in a face recognition system. However, human faces in wild conditions often present large variations in shape due to different poses, occlusions or expressions, which ma...
详细信息
ISBN:
(纸本)9781479983407
Facial landmark detection is an important issue in a face recognition system. However, human faces in wild conditions often present large variations in shape due to different poses, occlusions or expressions, which makes it a difficult task. Instead of learning the same map for all images, we propose a Pose-Induced auto-encoder Networks (PIAN) approach which uses different pose-induced networks for landmark estimation under different pose conditions. Firstly, we build a network to simultaneously get the initial land-mark and pose estimation. Then, different networks which are induced by the estimated pose are built for local search where a component-based searching method is explored. By using the pose inducing strategy, the initial estimation is reliable and it helps reduce the variations in local patches. This makes the component-based search feasible and more accurate than previous searching methods. Experiments show that our method outperforms the state-of-the-art algorithms especially in terms of fine estimation of landmarks.
Reducing the dimensionality of image with high-dimensional feature plays a significant role in image retrieval and classification. Recently, two methods have been proposed to improve the efficiency and accuracy of dim...
详细信息
ISBN:
(纸本)9783642156953
Reducing the dimensionality of image with high-dimensional feature plays a significant role in image retrieval and classification. Recently, two methods have been proposed to improve the efficiency and accuracy of dimensionality reduction, one uses CUR matrix decompositions to construct low rank matrix approximations and another approach for dimension reduction trains an auto-encoder with deep architecture to learn low-dimensional codes. In this paper, after above two mentioned methods are respectively utilized to reduce the high-dimensional features of images, we train individual classifiers on both original and reduced feature space for image classification. This paper compares these two approaches with other approaches in image classification. At the same, we also study the effects of the depth of layers on the performance of dimensionality reduction using auto-encoder.
暂无评论