Single-Input Multi-Output U-Net for Automated 2D Foetal Brain Segmentation of MR Images

In this work, we develop the Single-Input Multi-Output U-Net (SIMOU-Net), a hybrid network for foetal brain segmentation inspired by the original U-Net fused with the holistically nested edge detection (HED) network. The SIMOU-Net is similar to the original U-Net but it has a deeper architecture and takes account of the features extracted from each side output. It acts similar to an ensemble neural network, however, instead of averaging the outputs from several independently trained models, which is computationally expensive, our approach combines outputs from a single network to reduce the variance of predications and generalization errors. Experimental results using 200 normal foetal brains consisting of over 11,500 2D images produced Dice and Jaccard coefficients of 94.2 ± 5.9% and 88.7 ± 6.9%, respectively. We further tested the proposed network on 54 abnormal cases (over 3500 images) and achieved Dice and Jaccard coefficients of 91.2 ± 6.8% and 85.7 ± 6.6%, respectively.

Unsupervised video object segmentation: An affinity and edge learning approach.

<div>This paper presents a new approach to solve unsupervised video object segmentation~(UVOS) problem (called TMNet). The UVOS is still a challenging problem as prior methods suffer from issues like generalization errors to segment multiple objects in unseen test videos (category agnostic), over reliance on inaccurate optic flow, and problem towards capturing fine details at object boundaries. These issues make the UVOS, particularly in presence of multiple objects, an ill-defined problem. Our focus is to constrain the problem and improve the segmentation results by inclusion of multiple available cues such as appearance, motion, image edge, flow edge and tracking information through neural attention. To solve the challenging category agnostic multiple object UVOS, our model is designed to predict neighbourhood affinities for being part of the same object and cluster those to obtain accurate segmentation. To achieve multi cue based neural attention, we designed a Temporal Motion Attention module, as part of our segmentation framework, to learn the spatio-temporal features. To refine and improve the accuracy of object segmentation boundaries, an edge refinement module (using image and optic flow edges) and a geometry based loss function are incorporated. The overall framework is capable of segmenting and finding accurate objects' boundaries without any heuristic post processing. This enables the method to be used for unseen videos. Experimental results on challenging DAVIS16 and multi object DAVIS17 datasets shows that our proposed TMNet performs favourably compared to the state-of-the-art methods without post processing.</div>

Unsupervised video object segmentation: An affinity and edge learning approach.

<div>This paper presents a new approach to solve unsupervised video object segmentation~(UVOS) problem (called TMNet). The UVOS is still a challenging problem as prior methods suffer from issues like generalization errors to segment multiple objects in unseen test videos (category agnostic), over reliance on inaccurate optic flow, and problem towards capturing fine details at object boundaries. These issues make the UVOS, particularly in presence of multiple objects, an ill-defined problem. Our focus is to constrain the problem and improve the segmentation results by inclusion of multiple available cues such as appearance, motion, image edge, flow edge and tracking information through neural attention. To solve the challenging category agnostic multiple object UVOS, our model is designed to predict neighbourhood affinities for being part of the same object and cluster those to obtain accurate segmentation. To achieve multi cue based neural attention, we designed a Temporal Motion Attention module, as part of our segmentation framework, to learn the spatio-temporal features. To refine and improve the accuracy of object segmentation boundaries, an edge refinement module (using image and optic flow edges) and a geometry based loss function are incorporated. The overall framework is capable of segmenting and finding accurate objects' boundaries without any heuristic post processing. This enables the method to be used for unseen videos. Experimental results on challenging DAVIS16 and multi object DAVIS17 datasets shows that our proposed TMNet performs favourably compared to the state-of-the-art methods without post processing.</div>

Proses Berpikir Siswa dalam Memperbaiki Kesalahan Generalisasi Pola Linier

AbstrakMasih banyak kesalahan yang dilakukan oleh siswa dalam menggeneralisasi pola linier yang disebabkan fokus pada data numerik. Siswa-siswa yang mengalami kesalahan ini penting diberikan kesempatan kembali untuk memperbaiki kesalahan dalam menggeneralisasi pola linier. Untuk itu, tujuan penelitian ini adalah menganalisis proses berpikir siswa dalam memperbaiki kesalahan generalisasi pola linier. Sesuai dengan tujuan penelitian tersebut, maka penelitian ini merupakan penelitian kualitatif deskriptif dengan pendekatan studi kasus terhadap 2 siswa kelas VIII sekolah menengah pertama yang berhasil memperbaiki kesalahan generalisasi pola linier. Hasil penelitian menunjukkan bahwa terdapat dua jenis proses berpikir dalam memperbaiki kesalahan generalisasi pola linier, yaitu memperbaiki dengan menguji dan mencoba, serta memperbaiki dengan mengganti strategi generalisasi. Proses memperbaiki dengan menguji dan mencoba terdiri dari tiga tahap, yaitu: tahap mencari beda, tahap menguji, dan tahap mencoba. Proses memperbaiki dengan mengganti strategi generalisasi terdiri dari tiga tahap, yaitu: tahap mencari beda, tahap mengganti strategi generalisasi, dan tahap menemukan rumus suku ke-n. Cara yang paling efektif untuk memperbaiki kesalahan generalisasi pola linier adalah dengan cara mengganti strategi. Students Thinking Processes in Correcting Errors of Linear Pattern GeneralizationAbstractThere are still many mistakes made by students in generalizing linear patterns due to the focus on numerical data. It is important for students who experience this error to be given another opportunity to correct errors in generalizing linear patterns. For this reason, the purpose of this study is to analyze students' thought processes in correcting errors in the generalization of linear patterns. By the objectives of this study, this research is a descriptive qualitative study with a case study approach to 2 students of class VIII junior high school who succeeded in correcting errors in the generalization of linear patterns. The results showed that there are two types of thought processes in correcting errors in the generalization of linear patterns, namely repairing by testing and trying, and improving by replacing generalization strategies. The process of improving by testing and trying consists of three stages, namely: the stage of finding a difference, the testing stage, and the trying stage. The process of improving by replacing the generalization strategy consists of three stages, namely: the stage of finding a difference, the stage of changing the generalization strategy, and the stage of finding the formula for the nth term. The most effective way to correct linear pattern generalization errors is by changing strategies.

FNNC: Achieving Fairness through Neural Networks

In classification models, fairness can be ensured by solving a constrained optimization problem. We focus on fairness constraints like Disparate Impact, Demographic Parity, and Equalized Odds, which are non-decomposable and non-convex. Researchers define convex surrogates of the constraints and then apply convex optimization frameworks to obtain fair classifiers. Surrogates serve as an upper bound to the actual constraints, and convexifying fairness constraints is challenging. We propose a neural network-based framework, \emph{FNNC}, to achieve fairness while maintaining high accuracy in classification. The above fairness constraints are included in the loss using Lagrangian multipliers. We prove bounds on generalization errors for the constrained losses which asymptotically go to zero. The network is optimized using two-step mini-batch stochastic gradient descent. Our experiments show that FNNC performs as good as the state of the art, if not better. The experimental evidence supplements our theoretical guarantees. In summary, we have an automated solution to achieve fairness in classification, which is easily extendable to many fairness constraints.

Physics-Driven Regularization of Deep Neural Networks for Enhanced Engineering Design and Analysis

In this paper, we introduce a physics-driven regularization method for training of deep neural networks (DNNs) for use in engineering design and analysis problems. In particular, we focus on the prediction of a physical system, for which in addition to training data, partial or complete information on a set of governing laws is also available. These laws often appear in the form of differential equations, derived from first principles, empirically validated laws, or domain expertise, and are usually neglected in a data-driven prediction of engineering systems. We propose a training approach that utilizes the known governing laws and regularizes data-driven DNN models by penalizing divergence from those laws. The first two numerical examples are synthetic examples, where we show that in constructing a DNN model that best fits the measurements from a physical system, the use of our proposed regularization results in DNNs that are more interpretable with smaller generalization errors, compared with other common regularization methods. The last two examples concern metamodeling for a random Burgers’ system and for aerodynamic analysis of passenger vehicles, where we demonstrate that the proposed regularization provides superior generalization accuracy compared with other common alternatives.