Abstract

Recently, the fundamental problem of unsupervised domain adaptation (UDA) on 3D point clouds has been motivated by a wide variety of applications in robotics, virtual reality, and scene understanding, to name a few. The point cloud data acquisition procedures manifest themselves as significant domain discrepancies and geometric variations among both similar and dissimilar classes. The standard domain adaptation methods developed for images do not directly translate to point cloud data because of their complex geometric nature. To address this challenge, we leverage the idea of multimodality and alignment between distributions. We propose a new UDA architecture for point cloud classification that benefits from multimodal contrastive learning to get better class separation in both domains individually. Further, the use of optimal transport (OT) aims at learning source and target data distributions jointly to reduce the cross-domain shift and provide a better alignment. We conduct a comprehensive empirical study on PointDA-10 and GraspNetPC-10 and show that our method achieves state-of-the-art performance on GraspNetPC-10 (with ≈ 4-12% margin) and best average performance on PointDA-10. Our ablation studies and decision boundary analysis also validate the significance of our contrastive learning module and OT alig

Abstract

Learning embeddings of any data largely depends on the ability of the target space to capture semantic relations. The widely used Euclidean space, where embeddings are represented as point vectors, is known to be lacking in its potential to exploit complex structures and relations. Contrary to standard Euclidean embeddings, in this work, we embed point clouds as discrete probability distributions in Wasserstein space. We build a contrastive learning setup to learn Wasserstein embeddings that can be used as a pre-training method with or without supervision towards any downstream task. We show that the features captured by Wasserstein embeddings are better in preserving the point cloud geometry, including both global and local information, thus resulting in improved quality embeddings. We perform exhaustive experiments and demonstrate the effectiveness of our method for point cloud classification, transfer learning, segmentation, and interpolation tasks over multiple datasets including synthetic and realworld objects. We also compare against recent methods that use Wasserstein space and show that our method outperforms them in all downstream tasks. Additionally, our study reveals a promising interpretation of capturing critical points of point clouds that makes our proposed method self-explainable.

Abstract

Absolute separable (AS) quantum states are those states from which it is impossible to create entanglement, even under global unitary operations. It is known from the resource theory of non- absolute separability that the set of absolute separable states forms a convex and compact set, and global unitaries are free operations. We show that the action of a quantum switch controlled by an ancilla qubit over the global unitaries can break this robustness of AS states and produce ordinary separable states. First, we consider bipartite qubit systems and find the effect of quantum switch starting from the states sitting on the boundary of the set of absolute separable states. As particular examples, we illustrate what happens to modified Werner states and Bell diagonal (BD) states. For the Bell diagonal states, we provide the structure for the set of AS BD states and show how the structure changes under the influence of a switch. Further, we consider numerical generalization of the global unitary operations and show that it is always possible to take AS states out of the convex set under switching operations. We also generalized our results in higher dimensions.

Abstract

We introduce an innovative approach to automated sleep stage classification using EOG signals, addressing the discomfort and impracticality associated with EEG data acquisition. In addition, it is important to note that this approach is untapped in the field, highlighting its potential for novel insights and contributions. Our proposed SE-Resnet-Transformer model provides an accurate classification of five distinct sleep stages from raw EOG signal. Extensive validation on publically available databases (SleepEDF-20, SleepEDF-78, and SHHS) reveals noteworthy performance, with macro-F1 scores of 74.72, 70.63, and 69.26, respectively. Our model excels in identifying REM sleep, a crucial aspect of sleep disorder investigations. We also provide insight into the internal mechanisms of our model using techniques such as 1D-GradCAM and t-SNE plots. Our method improves the accessibility of sleep stage classification while decreasing the need for EEG modalities. This development will have promising implications for healthcare and the incorporation of wearable technology into sleep studies, thereby advancing the field's potential for enhanced diagnostics and patient comfort.

Abstract

We focus on the problem of LiDAR point cloud based loop detection (or Finding) and closure (LDC) for mobile robots. State-of-the-art (SOTA) methods directly generate learned embeddings from a given point cloud, require large data augmentation, and are not robust to wide viewpoint variations in 6 Degrees-of-Freedom (DOF). Moreover, the absence of strong priors in an unstructured point cloud leads to highly inaccurate LDC. In this original approach, we propose independent roll and pitch canonicalization of point clouds using a common dominant ground plane. We discretize the canonicalized point clouds along the axis perpendicular to the ground plane leads to images similar to digital elevation maps (DEMs), which expose strong spatial priors in the scene. Our experiments show that LDC based on learnt embeddings from such DEMs is not only data efficient but also significantly more robust, and generalizable than the current SOTA. We report an (average precision for loop detection, mean absolute translation/rotation error) improvement of (8.4, 16.7/5.43)% on the KITTI08 sequence, and (11.0, 34.0/25.4)% on GPR10 sequence, over the current SOTA. To further test the robustness of our technique on point clouds in 6-DOF motion we create and opensource a custom dataset called LidarUrbanFly Dataset (LUF) which consists of point clouds obtained from a LiDAR mounted on a quadrotor. More details on our website https://gsc2001.github.io/FinderNet/

Abstract

Worldover, seismic design of buildings typically follows a prescriptive approach in which designers conform to a series of prescriptive code requirements in terms of both analysis and design procedures. Even though this prescriptive seismic design approach is time-tested and easily understandable by structural designers. In the recent past, performance-based seismic design has started to gain traction among structural designers. The performance-based seismic design allows designers to set performance objectives and design buildings to meet the targeted performance criteria. Due to its flexible nature, performance-based design has proven extremely useful for critical and lifeline buildings like hospitals and tall buildings. With a focus placed on performance objectives, designers utilizing performance-based seismic design are proficient in designing code exceeding buildings efficiently. Despite these cited benefits, performance-based design is still considered an uncommon practice in structural design, particularly in the developing countries. Hence, the present study aims to provide an overview and framework to practice performance-based seismic design. This work identifies and discusses the key differences between the prescriptive- and performance-based seismic design methods and also addresses the significance, application and implementation of performance-based seismic design of buildings. This paper makes an original contribution to the literature through a critical review of how the performance-based design withholds the opportunity to elevate the role of the structural engineers to which they are informed members of the community, where the structures they create not only perform according to design prescriptions, but also perform according to the needs of the owners, engineers, and society.

Abstract

We consider a distributed multi-user secret sharing setting consisting of a dealer, n storage nodes and m secrets where each user demands a t-subset of m secrets. The user downloads shares from the storage nodes based on the designed access structure and reconstructs its secrets. Earlier work in this setting dealt with the case of t = 1; in this work, we generalize it to natural numbers. We identify a necessary condition on the access structures to ensure weak secrecy. We also make a connection between the access structures for this problem and t-disjunct matrices. We apply various t-disjunct matrix constructions in this setting and compare their performance in terms of the number of storage nodes and communication complexity. We also derive bounds on the optimal communication complexity of a distributed secret sharing protocol. Finally, we characterize the capacity region of the DMUSS problem when the access structure is specified

Abstract

We show that there exists endotactic and strongly endotactic dynamical systems that are not weakly reversible and possess infinitely many steady states. We provide a few examples in two dimensions and an example in three dimensions that satisfy this property. In addition, we prove for some of these systems that there exist no weakly reversible mass-action systems that are dynamically equivalent to mass-action systems generated by these networks.

Abstract

Digital representations of 3D objects are increasingly being used for engineering, entertainment, education, etc. Efforts to search and retrieve digital 3D models from a collection have not attracted sufficient attention, unlike digital representations of documents, images, etc. Supervised methods are not feasible to solve this problem as a large collection of labelled 3D objects is difficult to create. This paper presents a self-supervised method to learn efficient embeddings of 3D mesh objects for ranked retrieval of similar objects. We propose a simple representation of mesh objects and an encoder-decoder architecture to learn the embedding. Extensive experiments show that our method is competitive with methods that need supervision while being more scalable to different object collections.

Abstract

Encrypted data is susceptible to side-channel attacks like usage and access analysis. Techniques like Oblivious-RAM (ORAM) and privacy information retrieval and writing aim to hide clients’ access pattern while accessing encrypted data on a distrusted server. However, current techniques are constructed for a single server model making them unsuitable and inefficient for contemporary distributed architectures. In our work, we address this problem and provide a solution to private information update using packed secret sharing. Our protocol, named “Private Information Update for Distributed Infrastructure” PIUDI, aims to mitigate the attacks to which PIR-Writing protocols are more susceptible in a distributed environment. Our scheme is secure in presence of up to t + k − 1 compromised parties where k is the size of the data set. We also provide an analysis of our protocol for computational efficiency and gas cost in blockchains.