Search arXiv⌕ Search

arXiv subjects

Yuan Yuan

Publications and source records attributed to Yuan Yuan.

At least 199 records · Page 11Linked to original sources
arXiv2022

Counting Like Human: Anthropoid Crowd Counting on Modeling the Similarity of Objects

The mainstream crowd counting methods regress density map and integrate it to obtain counting results. Since the density representation to one head accords to its adjacent distribution, it embeds the same category objects with variant values, while human beings counting models the invariant features namely similarity to objects. Inspired by this, we propose a rational and anthropoid crowd counting framework. To begin with, we leverage counting scalar as supervision signal, which provides global and implicit guidance to similar matters. Then, the large kernel CNN is utilized to imitate the paradigm of human beings which models invariant knowledge firstly and slides to compare similarity. Later, re-parameterization on pre-trained paralleled parameters is presented to cater to the inner-class variance on similarity comparison. Finally, the Random Scaling patches Yield (RSY) is proposed to facilitate similarity modeling on long distance dependencies. Extensive experiments on five challenging benchmarks in crowd counting show the proposed framework achieves state-of-the-art.

cs.CV↗
arXiv2022

Object Detection in Foggy Scenes by Embedding Depth and Reconstruction into Domain Adaptation

Most existing domain adaptation (DA) methods align the features based on the domain feature distributions and ignore aspects related to fog, background and target objects, rendering suboptimal performance. In our DA framework, we retain the depth and background information during the domain feature alignment. A consistency loss between the generated depth and fog transmission map is introduced to strengthen the retention of the depth information in the aligned features. To address false object features potentially generated during the DA process, we propose an encoder-decoder framework to reconstruct the fog-free background image. This reconstruction loss also reinforces the encoder, i.e., our DA backbone, to minimize false object features.Moreover, we involve our target data in training both our DA module and our detection module in a semi-supervised manner, so that our detection module is also exposed to the unlabeled target data, the type of data used in the testing stage. Using these ideas, our method significantly outperforms the state-of-the-art method (47.6 mAP against the 44.3 mAP on the Foggy Cityscapes dataset), and obtains the best performance on multiple real-image public datasets. Code is available at: https://github.com/VIML-CVDL/Object-Detection-in-Foggy-Scenes

cs.CV↗
arXiv2022

RSVG: Exploring Data and Models for Visual Grounding on Remote Sensing Data

In this paper, we introduce the task of visual grounding for remote sensing data (RSVG). RSVG aims to localize the referred objects in remote sensing (RS) images with the guidance of natural language. To retrieve rich information from RS imagery using natural language, many research tasks, like RS image visual question answering, RS image captioning, and RS image-text retrieval have been investigated a lot. However, the object-level visual grounding on RS images is still under-explored. Thus, in this work, we propose to construct the dataset and explore deep learning models for the RSVG task. Specifically, our contributions can be summarized as follows. 1) We build the new large-scale benchmark dataset of RSVG, termed RSVGD, to fully advance the research of RSVG. This new dataset includes image/expression/box triplets for training and evaluating visual grounding models. 2) We benchmark extensive state-of-the-art (SOTA) natural image visual grounding methods on the constructed RSVGD dataset, and some insightful analyses are provided based on the results. 3) A novel transformer-based Multi-Level Cross-Modal feature learning (MLCM) module is proposed. Remotely-sensed images are usually with large scale variations and cluttered backgrounds. To deal with the scale-variation problem, the MLCM module takes advantage of multi-scale visual features and multi-granularity textual embeddings to learn more discriminative representations. To cope with the cluttered background problem, MLCM adaptively filters irrelevant noise and enhances salient features. In this way, our proposed model can incorporate more effective multi-level and multi-modal features to boost performance. Furthermore, this work also provides useful insights for developing better RSVG models. The dataset and code will be publicly available at https://github.com/ZhanYang-nwpu/RSVG-pytorch.

cs.CV↗
arXiv2022

Immediate blowup of entropy-bounded classical solutions to the vacuum free boundary problem of non-isentropic compressible Navier--Stokes equations

This paper considers the immediate blowup of entropy-bounded classical solutions to the vacuum free boundary problem of non-isentropic compressible Navier-Stokes equations. The viscosities and the heat conductivity could be constants, or more physically, the degenerate, temperature-dependent functions which vanish on the vacuum boundary (i.e., $μ=\barμ θ^α, ~ λ=\barλ θ^α,~ κ=\barκ θ^α$, for constants $0\leq α\leq 1/(γ-1)$, $\barμ>0,~2\barμ+n\barλ\geq0,~\barκ\geq 0$, and adiabatic exponent $γ>1$). With prescribed decaying rate of the initial density across the vacuum boundary, we prove that: (1) for three-dimensional spherically symmetric flows with non-vanishing bulk viscosity and zero heat conductivity, entropy-bounded classical solutions do not exist for any small time, provided the initial velocity is expanding near the boundary; (2) for three-dimensional spherically symmetric flows with non-vanishing heat conductivity, the normal derivative of the temperature of the classical solution across the free boundary does not degenerate, and therefore the entropy immediately blowups if the decaying rate of the initial density is not of $1/(γ-1)$ power of the distance function to the boundary; (3) for one-dimensional flow with zero heat conductivity, the non-existence result is similar but need more restrictions on the decaying rate. Together with our previous results on local or global entropy-bounded classical solutions (Liu and Yuan, SIAM J. Math. Anal. (2) 51, 2019; Liu and Yuan, Math. Models Methods Appl. Sci. (9) 12, 2019), this paper shows the necessity of proper degenerate conditions on the density and temperature across the boundary for the well-posedness of the entropy-bounded classical solutions to the vacuum boundary problem of the viscous gas.

math.AP↗
arXiv2022

Learning Independent Instance Maps for Crowd Localization

Accurately locating each head's position in the crowd scenes is a crucial task in the field of crowd analysis. However, traditional density-based methods only predict coarse prediction, and segmentation/detection-based methods cannot handle extremely dense scenes and large-range scale-variations crowds. To this end, we propose an end-to-end and straightforward framework for crowd localization, named Independent Instance Map segmentation (IIM). Different from density maps and boxes regression, each instance in IIM is non-overlapped. By segmenting crowds into independent connected components, the positions and the crowd counts (the centers and the number of components, respectively) are obtained. Furthermore, to improve the segmentation quality for different density regions, we present a differentiable Binarization Module (BM) to output structured instance maps. BM brings two advantages into localization models: 1) adaptively learn a threshold map for different images to detect each instance more accurately; 2) directly train the model using loss on binary predictions and labels. Extensive experiments verify the proposed method is effective and outperforms the-state-of-the-art methods on the five popular crowd datasets. Significantly, IIM improves F1-measure by 10.4% on the NWPU-Crowd Localization task. The source code and pre-trained models will be released at https://github.com/taohan10200/IIM.

cs.CV↗
arXiv2022

Non-invasive color imaging through scattering medium under broadband illumination

Due to the complex of mixed spectral point spread function within memory effect range, it is unreliable and slow to use speckle correlation technology for non-invasive imaging through scattering medium under broadband illumination. The contrast of the speckles will drastically drop as the light source's spectrum width increases. Here, we propose a method for producing the optical transfer function with several speckle frames within memory effect range to image under broadband illumination. The method can be applied to image amplitude and color objects under white LED illumination. Compared to other approaches of imaging under broadband illumination, such as deep learning and modified phase retrieval, our method can provide more stable results with faster convergence speed, which can be applied in high speed scattering imaging under natural light illumination.

physics.optics↗
arXiv2022

MAFNet: A Multi-Attention Fusion Network for RGB-T Crowd Counting

RGB-Thermal (RGB-T) crowd counting is a challenging task, which uses thermal images as complementary information to RGB images to deal with the decreased performance of unimodal RGB-based methods in scenes with low-illumination or similar backgrounds. Most existing methods propose well-designed structures for cross-modal fusion in RGB-T crowd counting. However, these methods have difficulty in encoding cross-modal contextual semantic information in RGB-T image pairs. Considering the aforementioned problem, we propose a two-stream RGB-T crowd counting network called Multi-Attention Fusion Network (MAFNet), which aims to fully capture long-range contextual information from the RGB and thermal modalities based on the attention mechanism. Specifically, in the encoder part, a Multi-Attention Fusion (MAF) module is embedded into different stages of the two modality-specific branches for cross-modal fusion at the global level. In addition, a Multi-modal Multi-scale Aggregation (MMA) regression head is introduced to make full use of the multi-scale and contextual information across modalities to generate high-quality crowd density maps. Extensive experiments on two popular datasets show that the proposed MAFNet is effective for RGB-T crowd counting and achieves the state-of-the-art performance.

cs.CV↗
arXiv2022

Unsupervised Learning for Human Sensing Using Radio Signals

There is a growing literature demonstrating the feasibility of using Radio Frequency (RF) signals to enable key computer vision tasks in the presence of occlusions and poor lighting. It leverages that RF signals traverse walls and occlusions to deliver through-wall pose estimation, action recognition, scene captioning, and human re-identification. However, unlike RGB datasets which can be labeled by human workers, labeling RF signals is a daunting task because such signals are not human interpretable. Yet, it is fairly easy to collect unlabelled RF signals. It would be highly beneficial to use such unlabeled RF data to learn useful representations in an unsupervised manner. Thus, in this paper, we explore the feasibility of adapting RGB-based unsupervised representation learning to RF signals. We show that while contrastive learning has emerged as the main technique for unsupervised representation learning from images and videos, such methods produce poor performance when applied to sensing humans using RF signals. In contrast, predictive unsupervised learning methods learn high-quality representations that can be used for multiple downstream RF-based sensing tasks. Our empirical results show that this approach outperforms state-of-the-art RF-based human sensing on various tasks, opening the possibility of unsupervised representation learning from this novel modality.

cs.CV↗
arXiv2022

Uniform estimates of the Cauchy-Riemann equation on product domains

We observe that the continuity assumption on $f$ for the uniform estimates of the canonical solution to $\bar\partial u = f$ on products of $C^2$ bounded planar domains in \cite{DPZ} can be reduced to the boundedness assumption. This completely answers the original question raised by Kerzman in 1971. Moreover, the $L^p$ estimates of $\bar\partial$ is obtained for all $p \in [1, \infty]$.

math.CV↗
arXiv2022

The Chinese Hα Solar Explorer (CHASE) mission: An overview

The Chinese Hα Solar Explorer (CHASE), dubbed "Xihe" - Goddess of the Sun, was launched on October 14, 2021 as the first solar space mission of China National Space Administration (CNSA). The CHASE mission is designed to test a newly developed satellite platform and to acquire the spectroscopic observations in the Hα waveband. The Hα Imaging Spectrograph (HIS) is the scientific payload of the CHASE satellite. It consists of two observational modes: raster scanning mode and continuum imaging mode. The raster scanning mode obtains full-Sun or region-of-interest spectral images from 6559.7 to 6565.9 Å and from 6567.8 to 6570.6 Å with 0.024 Å pixel spectral resolution and 1 minute temporal resolution. The continuum imaging mode obtains photospheric images in continuum around 6689 Å with the full width at half maximum of 13.4 Å. The CHASE mission will advance our understanding of the dynamics of solar activity in the photosphere and chromosphere. In this paper, we present an overview of the CHASE mission including the scientific objectives, HIS instrument overview, data calibration flow, and first results of on-orbit observations.

astro-ph.SR↗
arXiv2022

Calibration procedures for the CHASE/HIS science data

The Hα line is an important optical line in solar observations containing the information from the photosphere to the chromosphere. To study the mechanisms of solar eruptions and the plasma dynamics in the lower atmosphere, the Chinese Hα Solar Explorer (CHASE) was launched into a Sun-synchronous orbit on October 14, 2021. The scientific payload of the CHASE satellite is the Hα Imaging Spectrograph (HIS). The CHASE/HIS acquires, for the first time, seeing-free Hα spectroscopic observations with high spectral and temporal resolutions. It consists of two observational modes. The raster scanning mode provides full-Sun or region-of-interest spectra at Hα (6559.7-6565.9 Å) and Fe I (6567.8-6570.6 Å) wavebands. The continuum imaging mode obtains full-Sun photospheric images at around 6689 Å. In this paper, we present detailed calibration procedures for the CHASE/HIS science data, including the dark-field and flat-field correction, slit image curvature correction, wavelength and intensity calibration, and coordinate transformation. The higher-level data products can be directly used for scientific research.

astro-ph.SR↗
arXiv2022

Targeted Supervised Contrastive Learning for Long-Tailed Recognition

Real-world data often exhibits long tail distributions with heavy class imbalance, where the majority classes can dominate the training process and alter the decision boundaries of the minority classes. Recently, researchers have investigated the potential of supervised contrastive learning for long-tailed recognition, and demonstrated that it provides a strong performance gain. In this paper, we show that while supervised contrastive learning can help improve performance, past baselines suffer from poor uniformity brought in by imbalanced data distribution. This poor uniformity manifests in samples from the minority class having poor separability in the feature space. To address this problem, we propose targeted supervised contrastive learning (TSC), which improves the uniformity of the feature distribution on the hypersphere. TSC first generates a set of targets uniformly distributed on a hypersphere. It then makes the features of different classes converge to these distinct and uniformly distributed targets during training. This forces all classes, including minority classes, to maintain a uniform distribution in the feature space, improves class boundaries, and provides better generalization even in the presence of long-tail data. Experiments on multiple datasets show that TSC achieves state-of-the-art performance on long-tailed recognition tasks.

cs.CV↗
arXiv2022

Dual-Stage Approach Toward Hyperspectral Image Super-Resolution

Hyperspectral image produces high spectral resolution at the sacrifice of spatial resolution. Without reducing the spectral resolution, improving the resolution in the spatial domain is a very challenging problem. Motivated by the discovery that hyperspectral image exhibits high similarity between adjacent bands in a large spectral range, in this paper, we explore a new structure for hyperspectral image super-resolution (DualSR), leading to a dual-stage design, i.e., coarse stage and fine stage. In coarse stage, five bands with high similarity in a certain spectral range are divided into three groups, and the current band is guided to study the potential knowledge. Under the action of alternative spectral fusion mechanism, the coarse SR image is super-resolved in band-by-band. In order to build model from a global perspective, an enhanced back-projection method via spectral angle constraint is developed in fine stage to learn the content of spatial-spectral consistency, dramatically improving the performance gain. Extensive experiments demonstrate the effectiveness of the proposed coarse stage and fine stage. Besides, our network produces state-of-the-art results against existing works in terms of spatial reconstruction and spectral fidelity.

eess.IV↗
arXiv2022

Investigating and Modeling the Dynamics of Long Ties

Long ties, the social ties that bridge different communities, are widely believed to play crucial roles in spreading novel information in social networks. However, some existing network theories and prediction models indicate that long ties might dissolve quickly or eventually become redundant, thus putting into question the long-term value of long ties. Our empirical analysis of real-world dynamic networks shows that contrary to such reasoning, long ties are more likely to persist than other social ties, and that many of them constantly function as social bridges without being embedded in local networks. Using a novel cost-benefit analysis model combined with machine learning, we show that long ties are highly beneficial, which instinctively motivates people to expend extra effort to maintain them. This partly explains why long ties are more persistent than what has been suggested by many existing theories and models. Overall, our study suggests the need for social interventions that can promote the formation of long ties, such as mixing people with diverse backgrounds.

cs.SI↗
arXiv2022

Dynamic-quenching of a single-photon avalanche photodetector using an adaptive resistive switch

One of the most common approaches for quenching single-photon avalanche diodes is to use a passive resistor in series with it. A drawback of this approach has been the limited recovery speed of the single-photon avalanche diodes. High resistance is needed to quench the avalanche, leading to slower recharging of the single-photon avalanche diodes depletion capacitor. We address this issue by replacing a fixed quenching resistor with a bias-dependent adaptive resistive switch. Reversible generation of metallic conduction enables switching between low and high resistance states under unipolar bias. As an example, using a Pt/Al2O3/Ag resistor with a commercial silicon single-photon avalanche diodes, we demonstrate avalanche pulse widths as small as ~30 ns, 10x smaller than a passively quenched approach, thus significantly improving the single-photon avalanche diodes frequency response. The experimental results are consistent with a model where the adaptive resistor dynamically changes its resistance during discharging and recharging the single-photon avalanche diodes.

physics.ins-det↗
arXiv2022

Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut

Transformers trained with self-supervised learning using self-distillation loss (DINO) have been shown to produce attention maps that highlight salient foreground objects. In this paper, we demonstrate a graph-based approach that uses the self-supervised transformer features to discover an object from an image. Visual tokens are viewed as nodes in a weighted graph with edges representing a connectivity score based on the similarity of tokens. Foreground objects can then be segmented using a normalized graph-cut to group self-similar regions. We solve the graph-cut problem using spectral clustering with generalized eigen-decomposition and show that the second smallest eigenvector provides a cutting solution since its absolute value indicates the likelihood that a token belongs to a foreground object. Despite its simplicity, this approach significantly boosts the performance of unsupervised object discovery: we improve over the recent state of the art LOST by a margin of 6.9%, 8.1%, and 8.1% respectively on the VOC07, VOC12, and COCO20K. The performance can be further improved by adding a second stage class-agnostic detector (CAD). Our proposed method can be easily extended to unsupervised saliency detection and weakly supervised object detection. For unsupervised saliency detection, we improve IoU for 4.9%, 5.2%, 12.9% on ECSSD, DUTS, DUT-OMRON respectively compared to previous state of the art. For weakly supervised object detection, we achieve competitive performance on CUB and ImageNet.

cs.CV↗
arXiv2022

Iterative Genetic Improvement: Scaling Stochastic Program Synthesis

Program synthesis aims to {\it automatically} find programs from an underlying programming language that satisfy a given specification. While this has the potential to revolutionize computing, how to search over the vast space of programs efficiently is an unsolved challenge in program synthesis. In cases where large programs are required for a solution, it is generally believed that {\it stochastic} search has advantages over other classes of search techniques. Unfortunately, existing stochastic program synthesizers do not meet this expectation very well, suffering from the scalability issue. Here we propose a new framework for stochastic program synthesis, called iterative genetic improvement to overcome this problem, a technique inspired by the practice of the software development process. The key idea of iterative genetic improvement is to apply genetic improvement to improve a current reference program, and then iteratively replace the reference program by the best program found. Compared to traditional stochastic synthesis approaches, iterative genetic improvement can build up the complexity of programs incrementally in a more robust way. We evaluate the approach on two program synthesis domains: list manipulation and string transformation. Our empirical results indicate that this method has considerable advantages over several representative stochastic program synthesizer techniques, both in terms of scalability and of solution quality.

cs.NE↗