arXiv subjects

Xin Pan

Publications and source records attributed to Xin Pan.

30 records · Page 2Linked to original sources

arXiv2023

Channel-Spatial-Based Few-Shot Bird Sound Event Detection

In this paper, we propose a model for bird sound event detection that focuses on a small number of training samples within the everyday long-tail distribution. As a result, we investigate bird sound detection using the few-shot learning paradigm. By integrating channel and spatial attention mechanisms, improved feature representations can be learned from few-shot training datasets. We develop a Metric Channel-Spatial Network model by incorporating a Channel Spatial Squeeze-Excitation block into the prototype network, combining it with these attention mechanisms. We evaluate the Metric Channel Spatial Network model on the DCASE 2022 Take5 dataset benchmark, achieving an F-measure of 66.84% and a PSDS of 58.98%. Our experiment demonstrates that the combination of channel and spatial attention mechanisms effectively enhances the performance of bird sound classification and detection.

eess.AS↗

arXiv2023

Application of the disk instability model to all Quasi-Periodic Eruptions

After the first quasi-periodic eruptions (QPEs, GSN069) was reported in 2019, four other sources have been identified as QPEs or its candidate. However, the physics behind QPEs is still unclear so far, though several models have been proposed. Pan et al. (2022) proposed an instability model for the accretion disk with magnetically driven outflows in the first QPEs GSN 069, which is able to reproduce both the light curve and the evolution of spectrum fairly well. In this work, we exploit this model to all the QPEs. We imporve the calculations of the spectrum of disk by introducing a hardening factor, which is caused by the deviation of opacity from the blackbody. We find that the light curves and evolution of the spectra of the four QPEs or candidate can all be well reproduced by our model calculations.

astro-ph.HE↗

arXiv2023

Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective

Post-training quantization (PTQ) is widely regarded as one of the most efficient compression methods practically, benefitting from its data privacy and low computation costs. We argue that an overlooked problem of oscillation is in the PTQ methods. In this paper, we take the initiative to explore and present a theoretical proof to explain why such a problem is essential in PTQ. And then, we try to solve this problem by introducing a principled and generalized framework theoretically. In particular, we first formulate the oscillation in PTQ and prove the problem is caused by the difference in module capacity. To this end, we define the module capacity (ModCap) under data-dependent and data-free scenarios, where the differentials between adjacent modules are used to measure the degree of oscillation. The problem is then solved by selecting top-k differentials, in which the corresponding modules are jointly optimized and quantized. Extensive experiments demonstrate that our method successfully reduces the performance drop and is generalized to different neural networks and PTQ methods. For example, with 2/4 bit ResNet-50 quantization, our method surpasses the previous state-of-the-art method by 1.9%. It becomes more significant on small model quantization, e.g. surpasses BRECQ method by 6.61% on MobileNetV2*0.5.

cs.CV↗

arXiv2023

FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation

Recently, open-vocabulary learning has emerged to accomplish segmentation for arbitrary categories of text-based descriptions, which popularizes the segmentation system to more general-purpose application scenarios. However, existing methods devote to designing specialized architectures or parameters for specific segmentation tasks. These customized design paradigms lead to fragmentation between various segmentation tasks, thus hindering the uniformity of segmentation models. Hence in this paper, we propose FreeSeg, a generic framework to accomplish Unified, Universal and Open-Vocabulary Image Segmentation. FreeSeg optimizes an all-in-one network via one-shot training and employs the same architecture and parameters to handle diverse segmentation tasks seamlessly in the inference procedure. Additionally, adaptive prompt learning facilitates the unified model to capture task-aware and category-sensitive concepts, improving model robustness in multi-task and varied scenarios. Extensive experimental results demonstrate that FreeSeg establishes new state-of-the-art results in performance and generalization on three segmentation tasks, which outperforms the best task-specific architectures by a large margin: 5.5% mIoU on semantic segmentation, 17.6% mAP on instance segmentation, 20.1% PQ on panoptic segmentation for the unseen class on COCO.

cs.CV↗

arXiv2023

Enhanced photovoltaic effect in graphene-silicon Schottky junction under mechanical manipulation

Graphene-silicon Schottky junction (GSJ) which has the potential for large-scale manufacturing and integration can bring new opportunities to Schottky solar cells for photovoltaic (PV) power conversion. However, the essential power conversion limitation for these devices lies in the small open-circuit voltage ($V_{oc}$), which depends on the Schottky barrier height (SBH). In this study, we introduce an electromechanical method based on the flexoelectric effect to enhance the PV efficiency in GSJ. By atomic force microscope (AFM) tip-based indentation and in situ current measurement, the current-voltage (I-V) responses under flexoelectric strain gradient are obtained. The $V_{oc}$ is observed to increase for up to 20$\%$, leading to an evident improvement of the power conversion efficiency. Our studies suggest that strain gradient may offer unprecedented opportunities for the development of GSJ based flexo-photovoltaic applications.

cond-mat.mtrl-sci↗

arXiv2022

Charge Crowding in Graphene-Silicon Diodes

The performance of nanoscale electronic devices based on a two-three dimensional (2D-3D) interface is significantly affected by the electrical contacts that interconnect these materials with external circuitry. This work investigates charge transport effects at the 2D-3D ohmic contact coupled with the thermionic injection model for graphene/Si Schottky junction. Here, w e focus on the intrinsic properties of graphene-metal contacts, paying particular attention to the nature of the contact failure mechanism under high electrical stress. According to our findings, severe current crowding (CC) effects in highly conductive electrical contact significantly affect device failure that can be reduced by spatially varying the contact properties and geometry. The impact of electrical breakdown on material degradation is systematically analyzed by atomic force, Raman, scanning electron, and energy dispersive X-ray spectroscopies. Our devices withstand high electrostatic discharge spikes over a longer period, manifesting high robustness and operational stability. This research paves the way towards a highly robust and reliable graphene/Si heterostructure in futuristic on-chip integration in dynamic switching. The methods we employed here can be extended for other nanoscale electronic devices based on 2D-3D interfaces

physics.app-ph↗

arXiv2022

Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios

Due to the complex attention mechanisms and model design, most existing vision Transformers (ViTs) can not perform as efficiently as convolutional neural networks (CNNs) in realistic industrial deployment scenarios, e.g. TensorRT and CoreML. This poses a distinct challenge: Can a visual neural network be designed to infer as fast as CNNs and perform as powerful as ViTs? Recent works have tried to design CNN-Transformer hybrid architectures to address this issue, yet the overall performance of these works is far away from satisfactory. To end these, we propose a next generation vision Transformer for efficient deployment in realistic industrial scenarios, namely Next-ViT, which dominates both CNNs and ViTs from the perspective of latency/accuracy trade-off. In this work, the Next Convolution Block (NCB) and Next Transformer Block (NTB) are respectively developed to capture local and global information with deployment-friendly mechanisms. Then, Next Hybrid Strategy (NHS) is designed to stack NCB and NTB in an efficient hybrid paradigm, which boosts performance in various downstream tasks. Extensive experiments show that Next-ViT significantly outperforms existing CNNs, ViTs and CNN-Transformer hybrid architectures with respect to the latency/accuracy trade-off across various vision tasks. On TensorRT, Next-ViT surpasses ResNet by 5.5 mAP (from 40.4 to 45.9) on COCO detection and 7.7% mIoU (from 38.8% to 46.5%) on ADE20K segmentation under similar latency. Meanwhile, it achieves comparable performance with CSWin, while the inference speed is accelerated by 3.6x. On CoreML, Next-ViT surpasses EfficientFormer by 4.6 mAP (from 42.6 to 47.2) on COCO detection and 3.5% mIoU (from 45.1% to 48.6%) on ADE20K segmentation under similar latency. Our code and models are made public at: https://github.com/bytedance/Next-ViT

cs.CV↗

arXiv2022

Axial constants and sectional regularity of homogeneous ideals

A notion of sectional regularity for a homogeneous ideal $I$, which measures the regularity of its generic sections with respect to linear spaces of various dimensions, is introduced. It is related to axial constants defined as the intercepts on the coordinate axes of the set of exponents of monomials in the reverse lexicographic generic initial ideal of $I$. The equivalence of these notions and several other homological and ideal-theoretic invariants is shown. It is also established that these equivalent invariants grow linearly for the family of powers of a given ideal.

math.AC↗

arXiv2022

Parallel Pre-trained Transformers (PPT) for Synthetic Data-based Instance Segmentation

Recently, Synthetic data-based Instance Segmentation has become an exceedingly favorable optimization paradigm since it leverages simulation rendering and physics to generate high-quality image-annotation pairs. In this paper, we propose a Parallel Pre-trained Transformers (PPT) framework to accomplish the synthetic data-based Instance Segmentation task. Specifically, we leverage the off-the-shelf pre-trained vision Transformers to alleviate the gap between natural and synthetic data, which helps to provide good generalization in the downstream synthetic data scene with few samples. Swin-B-based CBNet V2, SwinL-based CBNet V2 and Swin-L-based Uniformer are employed for parallel feature learning, and the results of these three models are fused by pixel-level Non-maximum Suppression (NMS) algorithm to obtain more robust results. The experimental results reveal that PPT ranks first in the CVPR2022 AVA Accessibility Vision and Autonomy Challenge, with a 65.155% mAP.

cs.CV↗

arXiv2022

A disk instability model for the quasi-periodic eruptions of GSN 069

GSN 069 is a recently discovered QPE (Quasi-periodic eruptions) source recurring about every 9 hours. The mechanism for the QPEs of GSN 069 is still unclear so far. In this work, a disk instability model is constructed to explain GSN 069 based on Pan et al. (2021) (PLC21), where the authors proposed a toy model for the repeating changing-look (CL) active galactic nuclei (AGN). We improve the work of PLC21 by including a non-zero viscous torque condition on the inner boundary of disk and adopting a general form for the viscous stress torque in Kerr metric. It is found that the 0.4-2 keV light curves, the light curves at different energy bands and the phase-resolved X-ray spectrum of GSN 069 can all be qualitatively reproduced by our model. Furthermore, the profiles of light curve in QPEs can be significantly changed by the parameter μin viscous torque equation, which implies that our model may also be applied to other QPEs.

astro-ph.GA↗

arXiv2021

The effects of large-scale magnetic fields on the model for repeating changing-look AGNs

Periodic outbursts are observed in several changing-look (CL) active galactic nuclei (AGNs). \citet{sniegowska_possible_2020} suggested a model to explain the repeating CL in these AGNs, where the periodic outbursts are triggered in a narrow unstable zone between an inner ADAF and outer thin disk. In this work, we intend to investigate the effects of large-scale magnetic fields on the limit cycle behaviors of CL AGNs. The winds driven by magnetic fields can significantly change the structure of thin disk by taking away the angular momentum and energy of the disk. It is found that the period of outburst in repeating CL AGNs can be substantially reduced by the magnetic fields. Conversely, if we keep the period unchanged, the outburst intensity can be raised for several times. These results can help to explain the observational properties of multiple CL AGNs. Besides the magnetic fields, the effects of transition radius $R_{\rm tr}$, the width of transition zone $ΔR$ and Shakura-Sunyaev parameter $α$ are also explored in this work.

astro-ph.GA↗

arXiv2017

YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video

We introduce a new large-scale data set of video URLs with densely-sampled object bounding box annotations called YouTube-BoundingBoxes (YT-BB). The data set consists of approximately 380,000 video segments about 19s long, automatically selected to feature objects in natural settings without editing or post-processing, with a recording quality often akin to that of a hand-held cell phone camera. The objects represent a subset of the MS COCO label set. All video segments were human-annotated with high-precision classification labels and bounding boxes at 1 frame per second. The use of a cascade of increasingly precise human annotations ensures a label accuracy above 95% for every class and tight bounding boxes. Finally, we train and evaluate well-known deep network architectures and report baseline figures for per-frame classification and localization to provide a point of comparison for future work. We also demonstrate how the temporal contiguity of video can potentially be used to improve such inferences. Please see the PDF file to find the URL to download the data. We hope the availability of such large curated corpus will spur new advances in video object detection and tracking.

cs.CV↗