In processing dense 3D point cloud data for semantic segmentation, current deep learning networks face challenges maintaining a sufficient neighbourhood search area, limiting their accuracy and scalability. Inspired by the human visual field, EyeNet++ introduces a novel multi-scale and multi-density input strategy, ensuring extensive spatial coverage of a neighbourhood search area while preserving detail. The network is designed to maximize feature extraction from these diverse inputs through innovative modules. Parallel feature processing, facilitated by Messenger Fusion Block, enables the efficient exchange of complementary features between input scales. The Dense Local Feature Aggregation Block enhances feature learning by expanding receptive fields and capturing local and global context. At the same time, the Feature Merge Block seamlessly integrates features from multiple scales and densities for comprehensive and precise representation. Validated on large-scale benchmark datasets such as SensatUrban, Toronto3D, DALES, YUTOSemantic, and Semantic3D, EyeNet++ achieves state-of-the-art performance on SensatUrban, Toronto3D, and YUTOSemantic, effectively addressing the challenges posed by dense point clouds in outdoor scenes with various object sizes. The source code is available at https://github.com/Yacovitch/EyeNet2.

Resource disaggregation has been proposed as a solution for resource under-utilization in data centers. However, host virtualization technologies, which are the basic building blocks for constructing data centers, are implemented without considering the disaggregated resources. In addition, we discover that a RDMA I/O unit plays a significant role in the performance of a disaggregated resource environment. In this study, we propose DEHype, which alleviates the inefficiency of the hypervisors utilized in a disaggregated environment by investigating host virtualization technologies that are suitable for disaggregated memory systems. Specifically, DEHype aims to identify and improve the performance issues associated with virtual machines through KVM/QEMU in a disaggregated resource environment. The results demonstrate the effectiveness of the proposed optimizations in improving the performance of disaggregated memory systems. DEHype achieves up to a 351% improvement over the state-of-the-art disaggregated memory system.

We propose a new transfer learning algorithm between tasks with different dynamics. The proposed algorithm solves an Imitation from Observation problem (IfO) to ground the source environment to the target task before learning an optimal policy in the grounded environment. The learned policy is deployed in the target task without additional training. A particular feature of our algorithm is the employment of multiple rollout policies during training with a goal to ground the environment more globally; hence, it is named as Multi-Policy Grounding (MPG). The quality of final policy is further enhanced via ensemble policy learning. We demonstrate the superiority of the proposed algorithm analytically and numerically. Numerical studies show that the proposed multi-policy approach allows comparable grounding with single policy approach with a fraction of target samples, hence the algorithm is able to maintain the quality of obtained policy even as the number of interactions with the target environment becomes extremely small.

Recently, there has been a significant growth in the development of rechargeable battery-powered devices such as electric vehicles, leading to an urgent need for reliable and safe batteries. The remaining useful life (RUL) is a critical health indicator of battery, which is defined as the remaining number of charge and recharge cycles before the state-of-health falls below a user-specified threshold under certain operating settings. Substantially, the RUL can be estimated by adaptive stochastic processes or advanced machine learning techniques. However, the existing approaches either assume over-simplified degradation pattern in accordance with physics laws leading to poor generalizability or act as a black box offering no interpretation. To address these limitations, in this article, we develop a pattern-driven degradation process by integrating a recursive Gaussian distribution with its mean learnt from a gated recurrent unit (GRU) driven degradation pattern to capture degradation fluctuation into the model. Due to the non-Markovian state transitions, a joint-learning sampling-based expectation maximization algorithm was developed to estimate model parameters based on historical observations. Finally, numerical studies using real battery data showed that the proposed method achieves over 3% and 40% higher accuracy in RUL prediction than the GRU and adaptive Wiener process, respectively.

As an emerging field in Machine Learning, Explainable AI (XAI) has been offering remarkable performance in interpreting the decisions made by Convolutional Neural Networks (CNNs). To achieve visual explanations for CNNs, methods based on class activation mapping and randomized input sampling have gained great popularity. However, the attribution methods based on these techniques provide lower-resolution and blurry explanation maps that limit their explanation power. To circumvent this issue, visualization based on various layers is sought. In this work, we collect visualization maps from multiple layers of the model based on an attribution-based input sampling technique and aggregate them to reach a fine-grained and complete explanation. We also propose a layer selection strategy that applies to the whole family of CNN-based models, based on which our extraction framework is applied to visualize the last layers of each convolutional block of the model. Moreover, we perform an empirical analysis of the efficacy of derived lower-level information to enhance the represented attributions. Comprehensive experiments conducted on shallow and deep models trained on natural and industrial datasets, using both ground-truth and model-truth based evaluation metrics validate our proposed algorithm by meeting or outperforming the state-of-the-art methods in terms of explanation ability and visual quality, demonstrating that our method shows stability regardless of the size of objects or instances to be explained.

Visualizing the features captured by Convolutional Neural Networks (CNNs) is one of the conventional approaches to interpret the predictions made by these models in numerous image recognition applications. Grad-CAM is a popular solution that provides such a visualization by combining the activation maps obtained from the model. However, the average gradient-based terms deployed in this method underestimates the contribution of the representations discovered by the model to its predictions. Addressing this problem, we introduce a solution to tackle this issue by computing the path integral of the gradient-based terms in Grad-CAM. We conduct a thorough analysis to demonstrate the improvement achieved by our method in measuring the importance of the extracted representations for the CNN’s predictions, which yields to our method’s administration in object localization and model interpretation.

Explainable AI (XAI) is an active research area to interpret a neural network’s decision by ensuring transparency and trust in the task-specified learned models. Recently, perturbation-based model analysis has shown better interpretation, but backpropagation techniques are still prevailing because of their computational efficiency. In this work, we combine both approaches as a hybrid visual explanation algorithm and propose an efficient interpretation method for convolutional neural networks. Our method adaptively selects the most critical features that mainly contribute towards a prediction to probe the model by finding the activated features. Experimental results show that the proposed method can reduce the execution time up to 30% while enhancing competitive interpretability without compromising the quality of explanation generated.

Current studies on digital rights management (DRM) have focused on security and encryption as a means of solving the issue of illegal copying by purchasers. In this paper, we propose a scheme that can adapt one DRM's DRM content to another DRM's DRM content in PAV (portable audio & video) device environments. The proposed DRM content adaptation is for making one DRM system use another DRM's DRM content which is protected by another DRM system.

Current studies on Digital Rights Management (DRM) have focused on security and encryption as a means of solving the issue of illegal copying by purchasers. In this paper, we propose an end-to-end key management scheme that can cover a content protection on the overall value-chains of content distribution. The proposed scheme can protect digital content from attacks since an encrypted content is sent by a first package server and only DRM client can decrypt the encrypted digital content. It makes it possible to protect content from content creator to purchaser.