随机梯度下降（SGD）是现代机器学习（ML）系统的基石。尽管具有其计算效率，但SGD仍需要随机数据访问，这些数据访问在依赖块可调地理的二级存储的系统中实现效率低下，例如HDD和SSD，例如TensorFlow/Pytorch和DB ML系统，而不是大文件。为了解决这种阻抗不匹配，已经提出了各种数据改组策略，以平衡SGD的收敛速率（有利于随机性）及其I/O性能（有利于顺序访问）。在本文中，我们首先对现有数据改组策略进行系统的实证研究，该研究表明，所有现有策略都有改进的空间 - 它们都在I/O性能或融合率方面受苦。考虑到这一点，我们提出了一种简单但新颖的分层数据改组策略Corgipile。与现有的策略相比，Corgipile避免了完整的数据洗牌，同时保持SGD的可比收敛速度，就好像执行了完整的混音一样。我们对Corgipile的融合行为提供了非平凡的理论分析。我们通过在新的CorgipileDataSet API中设计新的平行/分布式洗牌操作员来进一步将Corgipile整合到Pytorch中。我们还通过介绍具有优化的三个新的物理运营商，将Corgipile集成到PostgreSQL中。我们的实验结果表明，Corgipile可以与全面的SGD达到可比的收敛速率，以实现深度学习和广义线性模型。对于ImageNet数据集的深度学习模型，Corgipile比带有完整数据洗牌的Pytorch快1.5倍。对于具有线性模型的INDB ML，在HDD和SSD上，Corgipile的Corgipile比两个最先进的IN-DB ML系统（Apache Madlib和Bismarck）快1.6 x-12.8倍。

Ranking intuitionistic fuzzy sets with distance based ranking methods requires to calculate the distance between intuitionistic fuzzy set and a reference point which is known to have either maximum (positive ideal solution) or minimum (negative ideal solution) value. These group of approaches assume that as the distance of an intuitionistic fuzzy set to the reference point is decreases, the similarity of intuitionistic fuzzy set with that point increases. This is a misconception because an intuitionistic fuzzy set which has the shortest distance to positive ideal solution does not have to be the furthest from negative ideal solution for all circumstances when the distance function is nonlinear. This paper gives a mathematical proof of why this assumption is not valid for any of the non-linear distance functions and suggests a hypervolume based ranking approach as an alternative to distance based ranking. In addition, the suggested ranking approach is extended as a new multicriteria decision making method, HyperVolume based ASsessment (HVAS). HVAS is applied for multicriteria assessment of Turkey's energy alternatives. Results are compared with three well known distance based multicriteria decision making methods (TOPSIS, VIKOR, and CODAS).

Unsupervised object discovery aims to localize objects in images, while removing the dependence on annotations required by most deep learning-based methods. To address this problem, we propose a fully unsupervised, bottom-up approach, for multiple objects discovery. The proposed approach is a two-stage framework. First, instances of object parts are segmented by using the intra-image similarity between self-supervised local features. The second step merges and filters the object parts to form complete object instances. The latter is performed by two CNN models that capture semantic information on objects from the entire dataset. We demonstrate that the pseudo-labels generated by our method provide a better precision-recall trade-off than existing single and multiple objects discovery methods. In particular, we provide state-of-the-art results for both unsupervised class-agnostic object detection and unsupervised image segmentation.

A large portion of today's world population suffer from vision impairments and wear prescription eyeglasses. However, eyeglasses causes additional bulk and discomfort when used with augmented and virtual reality headsets, thereby negatively impacting the viewer's visual experience. In this work, we remedy the usage of prescription eyeglasses in Virtual Reality (VR) headsets by shifting the optical complexity completely into software and propose a prescription-aware rendering approach for providing sharper and immersive VR imagery. To this end, we develop a differentiable display and visual perception model encapsulating display-specific parameters, color and visual acuity of human visual system and the user-specific refractive errors. Using this differentiable visual perception model, we optimize the rendered imagery in the display using stochastic gradient-descent solvers. This way, we provide prescription glasses-free sharper images for a person with vision impairments. We evaluate our approach on various displays, including desktops and VR headsets, and show significant quality and contrast improvements for users with vision impairments.

Dexterous manipulation with anthropomorphic robot hands remains a challenging problem in robotics because of the high-dimensional state and action spaces and complex contacts. Nevertheless, skillful closed-loop manipulation is required to enable humanoid robots to operate in unstructured real-world environments. Reinforcement learning (RL) has traditionally imposed enormous interaction data requirements for optimizing such complex control problems. We introduce a new framework that leverages recent advances in GPU-based simulation along with the strength of imitation learning in guiding policy search towards promising behaviors to make RL training feasible in these domains. To this end, we present an immersive virtual reality teleoperation interface designed for interactive human-like manipulation on contact rich tasks and a suite of manipulation environments inspired by tasks of daily living. Finally, we demonstrate the complementary strengths of massively parallel RL and imitation learning, yielding robust and natural behaviors. Videos of trained policies, our source code, and the collected demonstration datasets are available at https://maltemosbach.github.io/interactive_ human_like_manipulation/.

We present a data-driven framework to automate the vectorization and machine interpretation of 2D engineering part drawings. In industrial settings, most manufacturing engineers still rely on manual reads to identify the topological and manufacturing requirements from drawings submitted by designers. The interpretation process is laborious and time-consuming, which severely inhibits the efficiency of part quotation and manufacturing tasks. While recent advances in image-based computer vision methods have demonstrated great potential in interpreting natural images through semantic segmentation approaches, the application of such methods in parsing engineering technical drawings into semantically accurate components remains a significant challenge. The severe pixel sparsity in engineering drawings also restricts the effective featurization of image-based data-driven methods. To overcome these challenges, we propose a deep learning based framework that predicts the semantic type of each vectorized component. Taking a raster image as input, we vectorize all components through thinning, stroke tracing, and cubic bezier fitting. Then a graph of such components is generated based on the connectivity between the components. Finally, a graph convolutional neural network is trained on this graph data to identify the semantic type of each component. We test our framework in the context of semantic segmentation of text, dimension and, contour components in engineering drawings. Results show that our method yields the best performance compared to recent image, and graph-based segmentation methods.

In this study, to address the current high earlydetection miss rate of colorectal cancer (CRC) polyps, we explore the potentials of utilizing transfer learning and machine learning (ML) classifiers to precisely and sensitively classify the type of CRC polyps. Instead of using the common colonoscopic images, we applied three different ML algorithms on the 3D textural image outputs of a unique vision-based surface tactile sensor (VS-TS). To collect realistic textural images of CRC polyps for training the utilized ML classifiers and evaluating their performance, we first designed and additively manufactured 48 types of realistic polyp phantoms with different hardness, type, and textures. Next, the performance of the used three ML algorithms in classifying the type of fabricated polyps was quantitatively evaluated using various statistical metrics.

In this paper, to address the sensitivity and durability trade-off of Vision-based Tactile Sensor (VTSs), we introduce a hyper-sensitive and high-fidelity VTS called HySenSe. We demonstrate that by solely changing one step during the fabrication of the gel layer of the GelSight sensor (as the most well-known VTS), we can substantially improve its sensitivity and durability. Our experimental results clearly demonstrate the outperformance of the HySenSe compared with a similar GelSight sensor in detecting textural details of various objects under identical experimental conditions and low interaction forces (<= 1.5 N).

Digital sensors can lead to noisy results under many circumstances. To be able to remove the undesired noise from images, proper noise modeling and an accurate noise parameter estimation is crucial. In this project, we use a Poisson-Gaussian noise model for the raw-images captured by the sensor, as it fits the physical characteristics of the sensor closely. Moreover, we limit ourselves to the case where observed (noisy), and ground-truth (noise-free) image pairs are available. Using such pairs is beneficial for the noise estimation and is not widely studied in literature. Based on this model, we derive the theoretical maximum likelihood solution, discuss its practical implementation and optimization. Further, we propose two algorithms based on variance and cumulant statistics. Finally, we compare the results of our methods with two different approaches, a CNN we trained ourselves, and another one taken from literature. The comparison between all these methods shows that our algorithms outperform the others in terms of MSE and have good additional properties.

Image noise can often be accurately fitted to a Poisson-Gaussian distribution. However, estimating the distribution parameters from a noisy image only is a challenging task. Here, we study the case when paired noisy and noise-free samples are accessible. No method is currently available to exploit the noise-free information, which may help to achieve more accurate estimations. To fill this gap, we derive a novel, cumulant-based, approach for Poisson-Gaussian noise modeling from paired image samples. We show its improved performance over different baselines, with special emphasis on MSE, effect of outliers, image dependence, and bias. We additionally derive the log-likelihood function for further insights and discuss real-world applicability.