Search

Dynamic and interactive traffic scenarios pose significant challenges for autonomous driving systems. Reinforcement learning (RL) offers a promising approach by enabling the exploration of driving policies beyond the constraints of pre-collected datasets and predefined conditions, particularly in complex environments. However, a critical challenge lies in effectively extracting spatial and temporal features from sequences of high-dimensional, multi-modal observations while minimizing the accumulation of errors over time. Additionally, efficiently guiding large-scale RL models to converge on optimal driving policies without frequent failures during the training process remains tricky. We propose an end-to-end model-based RL algorithm named Ramble to address these issues. Ramble processes multi-view RGB images and LiDAR point clouds into low-dimensional latent features to capture the context of traffic scenarios at each time step. A transformer-based architecture is then employed to model temporal dependencies and predict future states. By learning a dynamics model of the environment, Ramble can foresee upcoming traffic events and make more informed, strategic decisions. Our implementation demonstrates that prior experience in feature extraction and decision-making plays a pivotal role in accelerating the convergence of RL models toward optimal driving policies. Ramble achieves state-of-the-art performance regarding route completion rate and driving score on the CARLA Leaderboard 2.0, showcasing its effectiveness in managing complex and dynamic traffic situations., Comment: 10 pages, 3 figures, experiment under progress, only to demonstrate the originality of the method

Semantic segmentation plays an important role in intelligent vehicles, providing pixel-level semantic information about the environment. However, the labeling budget is expensive and time-consuming when semantic segmentation model is applied to new driving scenarios. To reduce the costs, semi-supervised semantic segmentation methods have been proposed to leverage large quantities of unlabeled images. Despite this, their performance still falls short of the accuracy required for practical applications, which is typically achieved by supervised learning. A significant shortcoming is that they typically select unlabeled images for annotation randomly, neglecting the assessment of sample value for model training. In this paper, we propose a novel semi-supervised active domain adaptation (SS-ADA) framework for semantic segmentation that employs an image-level acquisition strategy. SS-ADA integrates active learning into semi-supervised semantic segmentation to achieve the accuracy of supervised learning with a limited amount of labeled data from the target domain. Additionally, we design an IoU-based class weighting strategy to alleviate the class imbalance problem using annotations from active learning. We conducted extensive experiments on synthetic-to-real and real-to-real domain adaptation settings. The results demonstrate the effectiveness of our method. SS-ADA can achieve or even surpass the accuracy of its supervised learning counterpart with only 25% of the target labeled data when using a real-time segmentation model. The code for SS-ADA is available at https://github.com/ywher/SS-ADA., Comment: 12 pages,13 figures,8 tables

In the hierarchical evolution framework of cosmology, larger halos grow through matter accretion and halo mergers. To clarify the halo evolution, we need to define the halo mass and radius physically. However, the pseudo-evolution problem makes the process difficult. Thus, we aim to measure the splashback radius, a physically defined halo radius for a large number of halos with various mass and redshift, and to determine the most important parameters to affect it. We use the typical definition of splashback radius (Rsp) as the radius with the steepest radial density profile. In this work, we measure Rsp of dark matter halos within the mass of 1e13-3e15Msun and redshifts spanning 0.08-0.65. This is the measurement of the Rsp in the largest range of halo mass and redshift. Using the shear catalog of the DECaLS DR8, we investigate Rsp of halos associated with galaxies and galaxy clusters identified in the various catalogs. Our finding reveals a trend wherein massive halos demonstrate a larger Rsp, and the normalized splashback radius (Rsp/R200m) shows a U-shaped mass evolution. The upturn in these relations mainly comes from the contribution of massive halos with low redshifts. We further find Rsp increases with the peak height, while Rsp/R200m has a negative relation with the peak height. We also find the Rsp >~R200m for most halos, indicating their low accretion rates. Our result is consistent with previous literature across a wide range of mass, redshift, and peak height, as well as the simulation work from More et al. (2015)., Comment: 15 pages, 7 figures, submitted to ApJ

Automated parking stands as a highly anticipated application of autonomous driving technology. However, existing path planning methodologies fall short of addressing this need due to their incapability to handle the diverse and complex parking scenarios in reality. While non-learning methods provide reliable planning results, they are vulnerable to intricate occasions, whereas learning-based ones are good at exploration but unstable in converging to feasible solutions. To leverage the strengths of both approaches, we introduce Hybrid pOlicy Path plannEr (HOPE). This novel solution integrates a reinforcement learning agent with Reeds-Shepp curves, enabling effective planning across diverse scenarios. HOPE guides the exploration of the reinforcement learning agent by applying an action mask mechanism and employs a transformer to integrate the perceived environmental information with the mask. To facilitate the training and evaluation of the proposed planner, we propose a criterion for categorizing the difficulty level of parking scenarios based on space and obstacle distribution. Experimental results demonstrate that our approach outperforms typical rule-based algorithms and traditional reinforcement learning methods, showing higher planning success rates and generalization across various scenarios. We also conduct real-world experiments to verify the practicability of HOPE. The code for our solution will be openly available on \href{GitHub}{https://github.com/jiamiya/HOPE}., Comment: 10 pages, 6 tables, 5 figures, 4 page appendix

Multispectral pedestrian detection has been shown to be effective in improving performance within complex illumination scenarios. However, prevalent double-stream networks in multispectral detection employ two separate feature extraction branches for multi-modal data, leading to nearly double the inference time compared to single-stream networks utilizing only one feature extraction branch. This increased inference time has hindered the widespread employment of multispectral pedestrian detection in embedded devices for autonomous systems. To address this limitation, various knowledge distillation methods have been proposed. However, traditional distillation methods focus only on the fusion features and ignore the large amount of information in the original multi-modal features, thereby restricting the student network's performance. To tackle the challenge, we introduce the Adaptive Modal Fusion Distillation (AMFD) framework, which can fully utilize the original modal features of the teacher network. Specifically, a Modal Extraction Alignment (MEA) module is utilized to derive learning weights for student networks, integrating focal and global attention mechanisms. This methodology enables the student network to acquire optimal fusion strategies independent from that of teacher network without necessitating an additional feature fusion module. Furthermore, we present the SMOD dataset, a well-aligned challenging multispectral dataset for detection. Extensive experiments on the challenging KAIST, LLVIP and SMOD datasets are conducted to validate the effectiveness of AMFD. The results demonstrate that our method outperforms existing state-of-the-art methods in both reducing log-average Miss Rate and improving mean Average Precision. The code is available at https://github.com/bigD233/AMFD.git.

Cluster-scale strong lensing is a powerful tool for exploring the properties of dark matter and constraining cosmological models. However, due to the complex parameter space, pixelized strong lens modeling in galaxy clusters is computationally expensive, leading to the point-source approximation of strongly lensed extended images, potentially introducing systematic biases. Herein, as the first paper of the ClUsteR strong Lens modelIng for the Next-Generation observations (CURLING) program, we use lensing ray-tracing simulations to quantify the biases and uncertainties arising from the point-like image approximation for JWST-like observations. Our results indicate that the approximation works well for reconstructing the total cluster mass distribution, but can bias the magnification measurements near critical curves and the constraints on the cosmological parameters, the total matter density of the Universe $\Omega_{\rm m}$, and dark energy equation of state parameter $w$. To mitigate the biases, we propose incorporating the extended surface brightness distribution of lensed sources into the modeling. This approach reduces the bias in magnification from 46.2 per cent to 0.09 per cent for $\mu \sim 1000$. Furthermore, the median values of cosmological parameters align more closely with the fiducial model. In addition to the improved accuracy, we also demonstrate that the constraining power can be substantially enhanced. In conclusion, it is necessary to model cluster-scale strong lenses with pixelized multiple images, especially for estimating the intrinsic luminosity of highly magnified sources and accurate cosmography in the era of high-precision observations., Comment: 12 pages, 8 figures

Simulators play a crucial role in autonomous driving, offering significant time, cost, and labor savings. Over the past few years, the number of simulators for autonomous driving has grown substantially. However, there is a growing concern about the validity of algorithms developed and evaluated in simulators, indicating a need for a thorough analysis of the development status of the simulators. To bridge the gap in research, this paper analyzes the evolution of simulators and explains how the functionalities and utilities have developed. Then, the existing simulators are categorized based on their task applicability, providing researchers with a taxonomy to swiftly assess a simulator's suitability for specific tasks. Recommendations for select simulators are presented, considering factors such as accessibility, maintenance status, and quality. Recognizing potential hazards in simulators that could impact the confidence of simulation experiments, the paper dedicates substantial effort to identifying and justifying critical issues in actively maintained open-source simulators. Moreover, the paper reviews potential solutions to address these issues, serving as a guide for enhancing the credibility of simulators., Comment: 18 pages, 5 figures, 8 tables

Simulation is a prospective method for generating diverse and realistic traffic scenarios to aid in the development of driving decision-making systems. However, existing simulators often fall short in diverse scenarios or interactive behavior models for traffic participants. This deficiency underscores the need for a flexible, reliable, user-friendly open-source simulator. Addressing this challenge, Tactics2D adopts a modular approach to traffic scenario construction, encompassing road elements, traffic regulations, behavior models, physics simulations for vehicles, and event detection mechanisms. By integrating numerous commonly utilized algorithms and configurations, Tactics2D empowers users to construct their driving scenarios effortlessly, just like assembling building blocks. Users can effectively evaluate the performance of driving decision-making models across various scenarios by leveraging both public datasets and user-collected real-world data. For access to the source code and community support, please visit the official GitHub page for Tactics2D at https://github.com/WoodOxen/Tactics2D., Comment: 6 pages, 1 figure, 2 tables

We try to understand the trends in the mass density slopes as a function of galaxy properties. We use the results from the best Jeans Anisotropic Modelling (JAM) of the integral-field stellar kinematics for near 6000 galaxies from the MaNGA DynPop project, with stellar masses of $10^{9-12}\ {\rm M_{\odot}}$, including both early-type and late-type galaxies. We use the mass-weighted density slopes for the stellar $\overline{\gamma}_*$, dark $\overline{\gamma}_{\rm DM}$, and total $\overline{\gamma}_{\rm T}$ mass from the MaNGA DynPop project. The $\overline{\gamma}_{\rm T}$ approaches a constant value of 2.2 for high $\sigma_{\rm e}$ galaxies, and flattens for lg$(\sigma_{\rm e}/{\rm km\ s^{-1}})\lesssim2.3$, reaching 1.5 for lg$(\sigma_{\rm e}/{\rm km\ s^{-1}})\approx1.8$. The total and stellar slopes track each other tightly, with $\overline{\gamma}_{\rm T}\approx\overline{\gamma}_*-0.174$ over the full $\sigma_{\rm e}$ range. This confirms the dominance of stellar matter within $R_{\rm e}$. We also show that there is no perfect conspiracy between baryonic and dark matter, as $\overline{\gamma}_*$ and $\overline{\gamma}_{\rm DM}$ do not vary inversely within the $\sigma_{\rm e}$ range. We find that the central galaxies from TNG50 and TNG100 simulations do not reproduce the observed galaxy mass distribution, which we attribute to the overestimated dark matter fraction, possibly due to a constant IMF and excessive adiabatic contraction effects in the simulations. Finally, we present the stacked dark matter density profiles and show that they are slightly steeper than the pure dark matter simulation prediction of $\overline{\gamma}_{\rm DM}\approx1$, suggesting moderate adiabatic contraction in the central region of galaxies. Our work demonstrate the power of stellar dynamics modelling for probing the interaction between stellar and dark matter and testing galaxy formation theories., Comment: 17 pages, 14 figures; accepted by MNRAS

The galaxy-galaxy lensing technique allows us to measure the subhalo mass of satellite galaxies, studying their mass loss and evolution within galaxy clusters and providing direct observational validation for theories of galaxy formation. In this study, we use the weak gravitational lensing observations from DECaLS DR8, in combination with the redMaPPer galaxy cluster catalog from Sloan Digital Sky Survey data (SDSS) DR8 to accurately measure the dark matter halo mass of satellite galaxies. We confirm a significant increase in the stellar-to-halo mass ratio of satellite galaxies with their halo-centric radius, indicating clear evidence of mass loss due to tidal stripping. Additionally, we find that this mass loss is strongly dependent on the mass of the satellite galaxies, with satellite galaxies above $10^{11}~{\rm M_{\odot}/h}$ experiencing more pronounced mass loss compared to lower mass satellites, reaching 86\% at projected halo-centric radius $0.5R_{\rm 200c}$. The average mass loss rate, when not considering halo-centric radius, displays a U-shaped variation with stellar mass, with galaxies of approximately $4\times10^{10}~{\rm M_{\odot}/h}$ exhibiting the least mass loss, around 60\%. We compare our results with state-of-the-art hydrodynamical numerical simulations and find that the satellite galaxy stellar-to-halo mass ratio in the outskirts of galaxy clusters is higher compared to the predictions of the Illustris-TNG project about factor 5. Furthermore, the Illustris-TNG project's numerical simulations did not predict the observed dependence of satellite galaxy mass loss rate on satellite galaxy mass., Comment: 14 pages, 9 figures

We present the measurement of total and stellar/dark matter decomposed mass density profile around a sample of galaxy groups and clusters with dynamical masses derived from integral-field stellar kinematics from the MaNGA survey in Paper I and weak lensing derived from the DECaLS imaging survey. Combining the two data sets enables accurate measurement of the radial density distribution from several kpc to Mpc scales. Intriguingly, we find that the excess surface density derived from stellar kinematics in the inner region cannot be explained by simply adding an NFW dark matter halo extrapolated from lensing measurement at a larger scale to a stellar mass component derived from the NASA-Sloan Atlas (NSA) catalogue. We find that a good fit to both data sets requires a stellar mass normalization about 3 times higher than that derived from the NSA catalogue, which would require an unrealistically too-heavy initial mass function for stellar mass estimation. If we keep the stellar mass normalization to that of the NSA catalogue but allow a varying inner dark matter density profile, we obtain an asymptotic slope of $\gamma_{\rm gnfw}$= $1.82_{-0.25}^{+0.15}$ and $\gamma_{\rm gnfw}$= $1.48_{-0.41}^{+0.20}$ for the group bin and the cluster bin respectively, significantly steeper than the NFW case. We also compare the total mass inner density slopes with those from TNG300 and find that the values from the simulation are lower than the observation by about $2\sigma$ level., Comment: 12 pages, 9 figures, accepted by MNRAS

Panoptic segmentation combines the advantages of semantic and instance segmentation, which can provide both pixel-level and instance-level environmental perception information for intelligent vehicles. However, it is challenged with segmenting objects of various scales, especially on extremely large and small ones. In this work, we propose two lightweight modules to mitigate this problem. First, Pixel-relation Block is designed to model global context information for large-scale things, which is based on a query-independent formulation and brings small parameter increments. Then, Convectional Network is constructed to collect extra high-resolution information for small-scale stuff, supplying more appropriate semantic features for the downstream segmentation branches. Based on these two modules, we present an end-to-end Scale-aware Unified Network (SUNet), which is more adaptable to multi-scale objects. Extensive experiments on Cityscapes and COCO demonstrate the effectiveness of the proposed methods., Comment: 10 pages, 7 figures, 8 tables

Semantic segmentation is an important task for intelligent vehicles to understand the environment. Current deep learning methods require large amounts of labeled data for training. Manual annotation is expensive, while simulators can provide accurate annotations. However, the performance of the semantic segmentation model trained with the data of the simulator will significantly decrease when applied in the actual scene. Unsupervised domain adaptation (UDA) for semantic segmentation has recently gained increasing research attention, aiming to reduce the domain gap and improve the performance on the target domain. In this paper, we propose a novel two-stage entropy-based UDA method for semantic segmentation. In stage one, we design a threshold-adaptative unsupervised focal loss to regularize the prediction in the target domain, which has a mild gradient neutralization mechanism and mitigates the problem that hard samples are barely optimized in entropy-based methods. In stage two, we introduce a data augmentation method named cross-domain image mixing (CIM) to bridge the semantic knowledge from two domains. Our method achieves state-of-the-art 58.4% and 59.6% mIoUs on SYNTHIA-to-Cityscapes and GTA5-to-Cityscapes using DeepLabV2 and competitive performance using the lightweight BiSeNet., Comment: 10 pages, 8 figure, 7 tables, submitted to T-ITS on April 2, 2022

We study the spectra of mixed graphs about its Hermitian adjacency matrix of the second kind (i.e. N-matrix) introduced by Mohar [1]. We extend some results and define one new Hermitian adjacency matrix, and the entry corresponding to an arc from $u$ to $v$ is equal to the $k$-th( or the third) root of unity, i.e. ${\omega} = cos(2{\pi}/k) + \textbf{i} \ sin(2{\pi}/k), k {\geq} 3$; the entry corresponding to an undirected edge is equal to 1, and 0 otherwise. In this paper, we characterize the cospectrality conditions for a mixed graph and its underlying graph. In section 4, we determine a sharp upper bound on the spectral radius of mixed graphs, and provide the corresponding extremal graphs., Comment: 14 pages, 5 figures

Thermal infrared (TIR) image has proven effectiveness in providing temperature cues to the RGB features for multispectral pedestrian detection. Most existing methods directly inject the TIR modality into the RGB-based framework or simply ensemble the results of two modalities. This, however, could lead to inferior detection performance, as the RGB and TIR features generally have modality-specific noise, which might worsen the features along with the propagation of the network. Therefore, this work proposes an effective and efficient cross-modality fusion module called Bi-directional Adaptive Attention Gate (BAA-Gate). Based on the attention mechanism, the BAA-Gate is devised to distill the informative features and recalibrate the representations asymptotically. Concretely, a bi-direction multi-stage fusion strategy is adopted to progressively optimize features of two modalities and retain their specificity during the propagation. Moreover, an adaptive interaction of BAA-Gate is introduced by the illumination-based weighting strategy to adaptively adjust the recalibrating and aggregating strength in the BAA-Gate and enhance the robustness towards illumination changes. Considerable experiments on the challenging KAIST dataset demonstrate the superior performance of our method with satisfactory speed.

The concentration-mass (c-M) relation encodes the key information of the assembly history of the dark matter halos, however its behavior at the high mass end has not been measured precisely in observations yet. In this paper, we report the measurement of halo c-M relation with galaxy-galaxy lensing method, using shear catalog of the Dark Energy Camera Legacy Survey (DECaLS) Data Release 8, which covers a sky area of 9500 deg^2. The foreground lenses are selected from redMaPPer, LOWZ, and CMASS catalogs, with halo mass range from 10^{13} to 10^{15} M_sun and redshift range from z=0.08 to z=0.65. We find that the concentration decreases with the halo mass from 10^{13} to 10^{14} M_sun, but shows a trend of upturn after the pivot point of ~10^{14} M_sun. We fit the measured c-M relation with the concentration model c(M)=C_0 (M/(10^{12} M_sun/h)^{-\gamma} [1+(M/M_0)^{0.4}], and get the values (C_0, \gamma, log(M_0) = (5.119_{-0.185}^{0.183}, 0.205_{-0.010}^{0.010}, 14.083_{-0.133}^{0.130}), and (4.875_{-0.208}^{0.209}, 0.221_{-0.010}^{0.010}, 13.750_{-0.141}^{0.142}) for halos with 0.08<=z<0.35 and 0.35<=z<0.65, respectively. We also show that the model including an upturn is favored over a simple power-law model. Our measurement provides important information for the recent argument of massive cluster formation process., Comment: 12 pages, 5 figures, accepted by ApJ

We present the Atacama Large Millimeter/submillimeter Array (ALMA) observation of the Sub-millimeter galaxy (SMG) ID 141 at z=4.24 in the [N II] 205 $\mu$m line (hereafter [N II]) and the underlying continuum at (rest-frame) 197.6 $\mu$m. Benefiting from lensing magnification by a galaxy pair at z=0.595, ID 141 is one of the brightest z$>4$ SMGs. At the angular resolutions of $\sim1.2"$ to $1.5"$ ($1" \sim6.9$ kpc), our observation clearly separates, and moderately resolves the two lensed images in both continuum and line emission at $\rm S/N>5$ . Our continuum-based lensing model implies an averaged amplification factor of $\sim5.8$ and reveals that the de-lensed continuum image has the S\'ersic index $\simeq 0.95$ and the S\'ersic radius of $\sim0.18" (\sim 1.24$ kpc). Furthermore, the reconstructed [N II] velocity field in the source plane is dominated by a rotation component with a maximum velocity of $\sim 300$ km/s at large radii, indicating a dark matter halo mass of $\sim 10^{12}M_{\odot}$. This, together with the reconstructed velocity dispersion field being smooth and modest in value ($<100$ km/s) over much of the outer parts of the galaxy, favours the interpretation of ID 141 being a disk galaxy dynamically supported by rotation. The observed [N II]/CO (7-6) and [N II]/[C II] 158 $\mu$m line luminosity ratios, which are consistent with the corresponding line ratio vs. far-infrared color correlation from local luminous infrared galaxies, imply a de-lensed star formation rate of ($1.8\pm 0.6)\times10^3M_\odot$/yr and provide an independent estimate on the size of the star-forming region $0.7^{+0.3}_{-0.3}$ kpc in radius., Comment: 13 pages, 6 figures, 2 tables. Lensing model code can be found here https://gitlab.com/cxylzlx/tiny_lens

As one of the most important tasks in autonomous driving systems, ego-lane detection has been extensively studied and has achieved impressive results in many scenarios. However, ego-lane detection in the missing feature scenarios is still an unsolved problem. To address this problem, previous methods have been devoted to proposing more complicated feature extraction algorithms, but they are very time-consuming and cannot deal with extreme scenarios. Different from others, this paper exploits prior knowledge contained in digital maps, which has a strong capability to enhance the performance of detection algorithms. Specifically, we employ the road shape extracted from OpenStreetMap as lane model, which is highly consistent with the real lane shape and irrelevant to lane features. In this way, only a few lane features are needed to eliminate the position error between the road shape and the real lane, and a search-based optimization algorithm is proposed. Experiments show that the proposed method can be applied to various scenarios and can run in real-time at a frequency of 20 Hz. At the same time, we evaluated the proposed method on the public KITTI Lane dataset where it achieves state-of-the-art performance. Moreover, our code will be open source after publication., Comment: There has some mistake in experiments

RGB-D semantic segmentation methods conventionally use two independent encoders to extract features from the RGB and depth data. However, there lacks an effective fusion mechanism to bridge the encoders, for the purpose of fully exploiting the complementary information from multiple modalities. This paper proposes a novel bottom-up interactive fusion structure to model the interdependencies between the encoders. The structure introduces an interaction stream to interconnect the encoders. The interaction stream not only progressively aggregates modality-specific features from the encoders but also computes complementary features for them. To instantiate this structure, the paper proposes a residual fusion block (RFB) to formulate the interdependences of the encoders. The RFB consists of two residual units and one fusion unit with gate mechanism. It learns complementary features for the modality-specific encoders and extracts modality-specific features as well as cross-modal features. Based on the RFB, the paper presents the deep multimodal networks for RGB-D semantic segmentation called RFBNet. The experiments on two datasets demonstrate the effectiveness of modeling the interdependencies and that the RFBNet achieved state-of-the-art performance.

We derive the mass weighted total density slopes within the effective (half-light) radius, $\gamma'$, for more than 2000 nearby galaxies from the SDSS-IV MaNGA survey using Jeans-anisotropic-models applied to IFU observations. Our galaxies span a wide range of the stellar mass ($10^9$ $M_{\rm \odot}< M_* < 10^{12}$ M$_{\odot}$) and the velocity dispersion (30 km/s $< \sigma_v <$ 300 km/s). We find that for galaxies with velocity dispersion $\sigma_v>100$ km/s, the density slope has a mean value $\langle \gamma^{\prime} \rangle = 2.24$ and a dispersion $\sigma_{\gamma}=0.22$, almost independent of velocity dispersion. A clear turn over in the $\gamma'-\sigma_v$ relation is present at $\sigma\sim 100$ km/s, below which the density slope decreases rapidly with $\sigma_v$. Our analysis shows that a large fraction of dwarf galaxies (below $M_* = 10^{10}$ M$_{\odot}$) have total density slopes shallower than 1, which implies that they may reside in cold dark matter halos with shallow density slopes. We compare our results with that of galaxies in hydrodynamical simulations of EAGLE, Illustris and IllustrisTNG projects, and find all simulations predict shallower density slopes for massive galaxies with high $\sigma_v$. Finally, we explore the dependence of $\gamma'$ on the positions of galaxies in halos, namely centrals vs. satellites, and find that for the same velocity dispersion, the amplitude of $\gamma'$ is higher for satellite galaxies by about 0.1., Comment: 11 pages, 10 figures, submitted to MNRAS

This paper introduces a novel approach for 3D semantic instance segmentation on point clouds. A 3D convolutional neural network called submanifold sparse convolutional network is used to generate semantic predictions and instance embeddings simultaneously. To obtain discriminative embeddings for each 3D instance, a structure-aware loss function is proposed which considers both the structure information and the embedding information. To get more consistent embeddings for each 3D instance, attention-based k nearest neighbour (KNN) is proposed to assign different weights for different neighbours. Based on the attention-based KNN, we add a graph convolutional network after the sparse convolutional network to get refined embeddings. Our network can be trained end-to-end. A simple mean-shift algorithm is utilized to cluster refined embeddings to get final instance predictions. As a result, our framework can output both the semantic prediction and the instance prediction. Experiments show that our approach outperforms all state-of-art methods on ScanNet benchmark and NYUv2 dataset.

Low mass galaxies are expected to be dark matter dominated even within their centrals. Recently two observations reported two dwarf galaxies in group environment with very little dark matter in their centrals. We explore the population and origins of dark-matter-deficient galaxies (DMDGs) in two state-of-the-art hydrodynamical simulations, the EAGLE and Illustris projects. For all satellite galaxies with $10^910^{13}$ M$_{\odot}$, we find that about $2.6\%$ of them in the EAGLE, and $1.5\%$ in the Illustris are DMDGs with dark matter fractions below $50\%$ inside two times half-stellar-mass radii. We demonstrate that DMDGs are highly tidal disrupted galaxies; and because dark matter has higher binding energy than stars, mass loss of the dark matter is much more rapid than stars in DMDGs during tidal interactions. If DMDGs were confirmed in observations, they are expected in current galaxy formation models., Comment: Updated to the accepted version

Let $A(G)$ be the adjacent matrix and $D(G)$ the diagonal matrix of the degrees of a graph $G$, respectively. For $0 \leq \alpha \leq 1$, the $A_{\alpha}$ matrix $A_{\alpha}(G) = \alpha D(G) +(1-\alpha)A(G)$ is given by Nikiforov. Clearly, $A_{0} (G)$ is the adjacent matrix and $2 A_{\frac{1}{2}}$ is the signless Laplacian matrix. A cactus is a connected graph such that any two of its cycles have at most one common vertex, that is an extension of the tree. The $A_{\alpha}$-spectral radius of a cactus graph with $n$ vertices and $k$ cycles is explored. The outcomes obtained in this paper can imply previous bounds of Nikiforov et al., and Lov\'{a}sz and Pelik\'{a}n. In addition, the corresponding extremal graphs are determined. Furthermore, we proposed all eigenvalues of such extremal cacti. Our results extended and enriched previous known results., Comment: submitted

The spatial distribution of satellite galaxies encodes rich information of the structure and assembly history of galaxy clusters. In this paper, we select a redMaPPer cluster sample in SDSS Stripe 82 region with $0.1 \le z \le 0.33$, $20<\lambda<100$ and $P_{\rm cen}>0.7$. Using the high-quality weak lensing data from CS82 Survey, we constrain the mass profile of this sample. Then we compare directly the mass density profile with the satellite number density profile. We find that the total mass and number density profiles have the same shape, both well fitted by an NFW profile. The scale radii agree with each other within 1$\sigma$ error ($r_{\rm s,gal}=0.34_{-0.03}^{+0.04}$Mpc vs $r_{\rm s}=0.37_{-0.10}^{+0.15}$Mpc )., Comment: 8 pages, 7 figures, 4 tables, accepted by mnras

Understanding the surrounding environment of the vehicle is still one of the challenges for autonomous driving. This paper addresses 360-degree road scene semantic segmentation using surround view cameras, which are widely equipped in existing production cars. First, in order to address large distortion problem in the fisheye images, Restricted Deformable Convolution (RDC) is proposed for semantic segmentation, which can effectively model geometric transformations by learning the shapes of convolutional filters conditioned on the input feature map. Second, in order to obtain a large-scale training set of surround view images, a novel method called zoom augmentation is proposed to transform conventional images to fisheye images. Finally, an RDC based semantic segmentation model is built; the model is trained for real-world surround view images through a multi-task learning architecture by combining real-world images with transformed images. Experiments demonstrate the effectiveness of the RDC to handle images with large distortions, and that the proposed approach shows a good performance using surround view cameras with the help of the transformed images.