物件導向軟體之架構(Object-Oriented Software Construction)探討

National Institute of Standards and Technology における超伝導研究及び生活

In the real world, a realistic setting for computer vision or multimedia recognition problems is that we have some classes containing lots of training data and many classes contain a small amount of training data. Therefore, how to use frequent classes to help learning rare classes for which it is harder to collect the training data is an open question. Learning with Shared Information is an emerging topic in machine learning, computer vision and multimedia analysis. There are different level of components that can be shared during concept modeling and machine learning stages, such as sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, etc. Regarding the specific methods, multi-task learning, transfer learning and deep learning can be seen as using different strategies to share information. These learning with shared information methods are very effective in solving real-world large-scale problems. This special issue aims at gathering the recent advances in learning with shared information methods and their applications in computer vision and multimedia analysis. Both state-of-the-art works, as well as literature reviews, are welcome for submission. Papers addressing interesting real-world computer vision and multimedia applications are especially encouraged. Topics of interest include, but are not limited to:  • Multi-task learning or transfer learning for large-scale computer vision and multimedia analysis • Deep learning for large-scale computer vision and multimedia analysis • Multi-modal approach for large-scale computer vision and multimedia analysis • Different sharing strategies, e.g., sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, • Real-world computer vision and multimedia applications based on learning with shared information, e.g., event detection, object recognition, object detection, action recognition, human head pose estimation, object tracking, location-based services, semantic indexing. • New datasets and metrics to evaluate the benefit of the proposed sharing ability for the specific computer vision or multimedia problem. • Survey papers regarding the topic of learning with shared information.  Authors who are unsure whether their planned submission is in scope may contact the guest editors prior to the submission deadline with an abstract, in order to receive feedback.

IEEE transactions on pattern analysis and machine intelligence

One of the main challenges in feature learning using Deep Convolutional Neural Networks (DCNNs) for large-scale face recognition is the design of appropriate loss functions that enhance discriminative power. Centre loss penalises the distance between the deep features and their corresponding class centres in the Euclidean space to achieve intra-class compactness. SphereFace assumes that the linear transformation matrix in the last fully connected layer can be used as a representation of the class centres in an angular space and penalises the angles between the deep features and their corresponding weights in a multiplicative way. Recently, a popular line of research is to incorporate margins in well-established loss functions in order to maximise face class separability. In this paper, we propose an Additive Angular Margin Loss (ArcFace) to obtain highly discriminative features for face recognition. The proposed ArcFace has a clear geometric interpretation due to the exact correspondence to the geodesic distance on the hypersphere. We present arguably the most extensive experimental evaluation of all the recent state-of-the-art face recognition methods on over 10 face recognition benchmarks including a new large-scale image database with trillion level of pairs and a large-scale video dataset. We show that ArcFace consistently outperforms the state-of-the-art and can be easily implemented with negligible computational overhead. We release all refined training data, training codes, pre-trained models and training logs, which will help reproduce the results in this paper.

ArcFace: Additive Angular Margin Loss for Deep Face Recognition

A methodology for evaluating range image segmentation algorithms is proposed. This methodology involves (1) a common set of 40 laser range finder images and 40 structured light scanner images that have manually specified ground truth and (2) a set of defined performance metrics for instances of correctly segmented, missed, and noise regions, over- and under-segmentation, and accuracy of the recovered geometry. A tool is used to objectively compare a machine generated segmentation against the specified ground truth. Four research groups have contributed to evaluate their own algorithm for segmenting a range image into planar patches.

An experimental comparison of range image segmentation algorithms

Translation invariant (TI) single wavelet denoising was developed by Coifman and Donoho (1994), and they show that TI is better than non-TI single wavelet denoising. On the other other hand, Strela et al. (1994) have found that non-TI multiwavelet denoising gives better results than non-TI single wavelets. We extend Coifman and Donoho's TI single wavelet denoising scheme to multiwavelets. Experimental results show that TI multiwavelet denoising is better than the single case for soft thresholding.

Translation-invariant denoising using multiwavelets

Multiwavelets give better results than single wavelets for signal denoising. We study multiwavelet thresholding by incorporating neighboring coefficients. Experimental results show that this approach is better than the conventional approach, which only uses the term-by-term multiwavelet denoising. Also, it outperforms neighbor single wavelet denoising for some standard test signals and real-life images. This is an extension to Cai and Silverman's (see Sankhya: Ind. J. Stat. B, pt.2, vol.63, p.127-148, 2001) work.

Multiwavelets denoising using neighboring coefficients

In this paper, we will present a novel framework of utilizing periocular region for age invariant face recognition. To obtain age invariant features, we first perform preprocessing schemes, such as pose correction, illumination and periocular region normalization. And then we apply robust Walsh-Hadamard transform encoded local binary patterns (WLBP) on preprocessed periocular region only. We find the WLBP feature on periocular region maintains consistency of the same individual across ages. Finally, we use unsupervised discriminant projection (UDP) to build subspaces on WLBP featured periocular images and gain 100% rank-1 identification rate and 98% verification rate at 0.1% false accept rate on the entire FG-NET database. Compared to published results, our proposed approach yields the best recognition and identification results.

Investigating age invariant face recognition based on periocular biometrics

In this paper, we introduce a novel age estimation technique that combines Active Appearance Models (AAMs) and Support Vector Machines (SVMs), to dramatically improve the accuracy of age estimation over the current state-of-the-art techniques. In this method, characteristics of the input images, face image, are interpreted as feature vectors by AAMs, which are used to discriminate between childhood and adulthood, prior to age estimation. Faces classified as adults are passed to the adult age-determination function and the others are passed to the child age-determination function. Compared to published results, this method yields the highest accuracy recognition rates, both in overall mean-absolute error (MAE) and mean-absolute error for the two periods of human development: childhood and adulthood.

Age estimation using Active Appearance Models and Support Vector Machine regression

Recently a variety of efficient image denoising methods using wavelet transforms have been proposed by many researchers. In this paper, we derive the general estimation rule in the wavelet domain to obtain the denoised coefficients from the noisy image based on the multivariate statistical theory. The multivariate distributions of the original clean image can be estimated empirically from a sample image set. We define a parametric multivariate generalized Gaussian distribution (MGGD) model which closely fits the sample distribution. Multivariate model makes it possible to exploit the dependency between the estimated wavelet coefficients and their neighbours or other coefficients in different subbands. Also it can be shown that some of the existing methods based on statistical modeling are subsets of our multivariate approach. Our method could achieve high quality image denoising. Among the existing image denoising methods using the same type of wavelet (Daubechies 8) filter, our results produce the highest peak signal-to-noise ratio (PSNR).

Tien D. Bui

Papers

Translation-invariant denoising using multiwavelets

Multiwavelets denoising using neighboring coefficients

Investigating age invariant face recognition based on periocular biometrics

Age estimation using Active Appearance Models and Support Vector Machine regression

Multivariate statistical modeling for image denoising using wavelet transforms