Search

Modern graphics processing units (GPUs) provide an unprecedented level of computing power. In this study, we present a high-performance, multi-GPU implementation of the analytical nuclear gradient for Kohn-Sham time-dependent density functional theory (TDDFT), employing the Tamm-Dancoff approximation (TDA) and Gaussian-type atomic orbitals as basis functions. We discuss GPU-efficient algorithms for the derivatives of electron repulsion integrals and exchange-correlation functionals within the range-separated scheme. As an illustrative example, we calculated the TDA-TDDFT gradient of the S1 state of a full-scale green fluorescent protein with explicit water solvent molecules, totaling 4353 atoms, at the wB97X/def2-SVP level of theory. Our algorithm demonstrates favorable parallel efficiencies on a high-speed distributed system equipped with 256 Nvidia A100 GPUs, achieving >70% with up to 64 GPUs and 31% with 256 GPUs, effectively leveraging the capabilities of modern high-performance computing systems., Comment: 13 pages, 9 figures

Monocular 3D object detection is an important challenging task in autonomous driving. Existing methods mainly focus on performing 3D detection in ideal weather conditions, characterized by scenarios with clear and optimal visibility. However, the challenge of autonomous driving requires the ability to handle changes in weather conditions, such as foggy weather, not just clear weather. We introduce MonoWAD, a novel weather-robust monocular 3D object detector with a weather-adaptive diffusion model. It contains two components: (1) the weather codebook to memorize the knowledge of the clear weather and generate a weather-reference feature for any input, and (2) the weather-adaptive diffusion model to enhance the feature representation of the input feature by incorporating a weather-reference feature. This serves an attention role in indicating how much improvement is needed for the input feature according to the weather conditions. To achieve this goal, we introduce a weather-adaptive enhancement loss to enhance the feature representation under both clear and foggy weather conditions. Extensive experiments under various weather conditions demonstrate that MonoWAD achieves weather-robust monocular 3D object detection. The code and dataset are released at https://github.com/VisualAIKHU/MonoWAD., Comment: Accepted by ECCV 2024

While federated learning leverages distributed client resources, it faces challenges due to heterogeneous client capabilities. This necessitates allocating models suited to clients' resources and careful parameter aggregation to accommodate this heterogeneity. We propose HypeMeFed, a novel federated learning framework for supporting client heterogeneity by combining a multi-exit network architecture with hypernetwork-based model weight generation. This approach aligns the feature spaces of heterogeneous model layers and resolves per-layer information disparity during weight aggregation. To practically realize HypeMeFed, we also propose a low-rank factorization approach to minimize computation and memory overhead associated with hypernetworks. Our evaluations on a real-world heterogeneous device testbed indicate that \system enhances accuracy by 5.12% over FedAvg, reduces the hypernetwork memory requirements by 98.22%, and accelerates its operations by 1.86x compared to a naive hypernetwork approach. These results demonstrate HypeMeFed's effectiveness in leveraging and engaging heterogeneous clients for federated learning.

Discovery of the Higgs boson decay to dimuon is anticipated soon based on the current evidence. Precise categorization of the events without affecting the invariant mass shape is crucial in the analysis. Decorrelation of the invariant mass and the output of discriminators (the score of discriminators) is essential for consistent and precise analysis. In this paper we use distance correlation as the additional loss function to achieve the decorrelation for discriminators and examine various analysis methods. The analyses with and without jet substructure variables are presented. Adding jet substructure variables considerably improves the significance of the Higgs to dimuon signal from gluon fusion., Comment: 25 pages, 7 figures, 7 tables: submitted to PRD

Computer vision applications predict on digital images acquired by a camera from physical scenes through light. However, conventional robustness benchmarks rely on perturbations in digitized images, diverging from distribution shifts occurring in the image acquisition process. To bridge this gap, we introduce a new distribution shift dataset, ImageNet-ES, comprising variations in environmental and camera sensor factors by directly capturing 202k images with a real camera in a controllable testbed. With the new dataset, we evaluate out-of-distribution (OOD) detection and model robustness. We find that existing OOD detection methods do not cope with the covariate shifts in ImageNet-ES, implying that the definition and detection of OOD should be revisited to embrace real-world distribution shifts. We also observe that the model becomes more robust in both ImageNet-C and -ES by learning environment and sensor variations in addition to existing digital augmentations. Lastly, our results suggest that effective shift mitigation via camera sensor control can significantly improve performance without increasing model size. With these findings, our benchmark may aid future research on robustness, OOD, and camera sensor control for computer vision. Our code and dataset are available at https://github.com/Edw2n/ImageNet-ES., Comment: Published as a conference paper at CVPR 2024

Recently, foundation models trained on massive datasets to adapt to a wide range of tasks have attracted considerable attention and are actively being explored within the computer vision community. Among these, the Segment Anything Model (SAM) stands out for its remarkable progress in generalizability and flexibility for image segmentation tasks, achieved through prompt-based object mask generation. However, despite its strength, SAM faces two key limitations when applied to instance segmentation that segments specific objects or those in unique environments (e.g., task-specific adaptation for out-of-distribution objects) not typically present in the training data: 1) the ambiguity inherent in input prompts and 2) the necessity for extensive additional training to achieve optimal segmentation. To address these challenges, we propose a task-specific adaptation (i.e., customization) of the segmentation foundation model via prompt learning tailored to SAM. Our method involves a prompt learning module (PLM), which adjusts input prompts into the embedding space to better align with peculiarities of the target task, thereby enabling more efficient training. Furthermore, we introduce a point matching module (PMM) to enhance the feature representation for finer segmentation by ensuring detailed alignment with ground truth boundaries. Experimental results on various customized segmentation scenarios demonstrate the effectiveness of the proposed method., Comment: Workshop on OOD Generalization in Computer Vision, ECCV 2024

Safe Multi-agent reinforcement learning (safe MARL) has increasingly gained attention in recent years, emphasizing the need for agents to not only optimize the global return but also adhere to safety requirements through behavioral constraints. Some recent work has integrated control theory with multi-agent reinforcement learning to address the challenge of ensuring safety. However, there have been only very limited applications of Model Predictive Control (MPC) methods in this domain, primarily due to the complex and implicit dynamics characteristic of multi-agent environments. To bridge this gap, we propose a novel method called Deep Learning-Based Model Predictive Control for Safe Multi-Agent Reinforcement Learning (DeepSafeMPC). The key insight of DeepSafeMPC is leveraging a entralized deep learning model to well predict environmental dynamics. Our method applies MARL principles to search for optimal solutions. Through the employment of MPC, the actions of agents can be restricted within safe states concurrently. We demonstrate the effectiveness of our approach using the Safe Multi-agent MuJoCo environment, showcasing significant advancements in addressing safety concerns in MARL., Comment: 8 pages, 5 figures

This paper investigates the number of scatterings a photon undergoes in random walks before escaping from a medium. The number of scatterings in random walk processes is commonly approximated as $\tau+\tau^2$ in the literature, where $\tau$ is the optical thickness measured from the center of the medium. However, it is found that this formula is not accurate. In this study, analytical solutions in sphere and slab geometries are derived for both optically thin and optically thick limits, assuming isotropic scattering. These solutions are verified using Monte Carlo simulations. In the optically thick limit, the number of scatterings is found to be $0.5\tau^2$ and $1.5\tau^2$ in a sphere and slab, respectively. In the optically thin limit, the number of scatterings is $\approx\tau$ in a sphere and $\approx\tau(1-\gamma-\ln\tau+\tau)$ in a slab, where $\gamma\simeq 0.57722$ is the Euler-Mascheroni constant. Additionally, we present approximate formulas that reasonably reproduce the simulation results well in intermediate optical depths. These results are applicable to scattering processes that exhibit forward and backward symmetry, including both isotropic and Thomson scattering., Comment: accepted for publication in JKAS

Obstructive sleep apnea (OSA) is a prevalent sleep disorder affecting approximately one billion people world-wide. The current gold standard for diagnosing OSA, Polysomnography (PSG), involves an overnight hospital stay with multiple attached sensors, leading to potential inaccuracies due to the first-night effect. To address this, we present SlAction, a non-intrusive OSA detection system for daily sleep environments using infrared videos. Recognizing that sleep videos exhibit minimal motion, this work investigates the fundamental question: "Are respiratory events adequately reflected in human motions during sleep?" Analyzing the largest sleep video dataset of 5,098 hours, we establish correlations between OSA events and human motions during sleep. Our approach uses a low frame rate (2.5 FPS), a large size (60 seconds) and step (30 seconds) for sliding window analysis to capture slow and long-term motions related to OSA. Furthermore, we utilize a lightweight deep neural network for resource-constrained devices, ensuring all video streams are processed locally without compromising privacy. Evaluations show that SlAction achieves an average F1 score of 87.6% in detecting OSA across various environments. Implementing SlAction on NVIDIA Jetson Nano enables real-time inference (~3 seconds for a 60-second video clip), highlighting its potential for early detection and personalized treatment of OSA., Comment: Accepted to ICCV CVAMD 2023, poster

This paper addresses the challenges of wideband signal beamforming in radar systems and proposes a new calibration method. Due to operating conditions, the frequency dependent characteristics of the system can be changed, and amplitude, phase, and time delay error can be generated. The proposed method is based on the concept of sliding window algorithm for linear frequency modulated (LFM) signals. To calibrate the frequency-dependent errors from transceiver and the time delay error from true time delay elements, the proposed method utilizes the characteristic of the LFM signal. The LFM signal changes its frequency linearly with time, and the frequency domain characteristics of the hardware are presented in time. Therefore, by applying matched filter to a part of the LFM signal, the frequency dependent characteristics can be monitored and calibrated. The proposed method is compared with the conventional matched filter based calibration results and verified by simulation results and beampatterns. Since the proposed method utilizes LFM signal as calibration tone, the proposed method can be applied to any beamforming systems, not limited to LFM radars., Comment: 11 pages