arXiv subjects

Li Sun

Publications and source records attributed to Li Sun.

At least 163 records · Page 9Linked to original sources

arXiv2022

EventPoint: Self-Supervised Interest Point Detection and Description for Event-based Camera

This paper proposes a self-supervised learned local detector and descriptor, called EventPoint, for event stream/camera tracking and registration. Event-based cameras have grown in popularity because of their biological inspiration and low power consumption. Despite this, applying local features directly to the event stream is difficult due to its peculiar data structure. We propose a new time-surface-like event stream representation method called Tencode. The event stream data processed by Tencode can obtain the pixel-level positioning of interest points while also simultaneously extracting descriptors through a neural network. Instead of using costly and unreliable manual annotation, our network leverages the prior knowledge of local feature extraction on color images and conducts self-supervised learning via homographic and spatio-temporal adaptation. To the best of our knowledge, our proposed method is the first research on event-based local features learning using a deep neural network. We provide comprehensive experiments of feature point detection and matching, and three public datasets are used for evaluation (i.e. DSEC, N-Caltech101, and HVGA ATIS Corner Dataset). The experimental findings demonstrate that our method outperforms SOTA in terms of feature point detection and description.

cs.CV↗

arXiv2022

IoU-Enhanced Attention for End-to-End Task Specific Object Detection

Without densely tiled anchor boxes or grid points in the image, sparse R-CNN achieves promising results through a set of object queries and proposal boxes updated in the cascaded training manner. However, due to the sparse nature and the one-to-one relation between the query and its attending region, it heavily depends on the self attention, which is usually inaccurate in the early training stage. Moreover, in a scene of dense objects, the object query interacts with many irrelevant ones, reducing its uniqueness and harming the performance. This paper proposes to use IoU between different boxes as a prior for the value routing in self attention. The original attention matrix multiplies the same size matrix computed from the IoU of proposal boxes, and they determine the routing scheme so that the irrelevant features can be suppressed. Furthermore, to accurately extract features for both classification and regression, we add two lightweight projection heads to provide the dynamic channel masks based on object query, and they multiply with the output from dynamic convs, making the results suitable for the two different tasks. We validate the proposed scheme on different datasets, including MS-COCO and CrowdHuman, showing that it significantly improves the performance and increases the model convergence speed.

cs.CV↗

arXiv2022

Hierarchical Amortized Training for Memory-efficient High Resolution 3D GAN

Generative Adversarial Networks (GAN) have many potential medical imaging applications, including data augmentation, domain adaptation, and model explanation. Due to the limited memory of Graphical Processing Units (GPUs), most current 3D GAN models are trained on low-resolution medical images, these models either cannot scale to high-resolution or are prone to patchy artifacts. In this work, we propose a novel end-to-end GAN architecture that can generate high-resolution 3D images. We achieve this goal by using different configurations between training and inference. During training, we adopt a hierarchical structure that simultaneously generates a low-resolution version of the image and a randomly selected sub-volume of the high-resolution image. The hierarchical design has two advantages: First, the memory demand for training on high-resolution images is amortized among sub-volumes. Furthermore, anchoring the high-resolution sub-volumes to a single low-resolution image ensures anatomical consistency between sub-volumes. During inference, our model can directly generate full high-resolution images. We also incorporate an encoder with a similar hierarchical structure into the model to extract features from the images. Experiments on 3D thorax CT and brain MRI demonstrate that our approach outperforms state of the art in image generation. We also demonstrate clinical applications of the proposed model in data augmentation and clinical-relevant feature extraction.

eess.IV↗

arXiv2022

PERFECT: A Hyperbolic Embedding for Joint User and Community Alignment

Social network alignment shows fundamental importance in a wide spectrum of applications. To the best of our knowledge, existing studies mainly focus on network alignment at the individual user level, requiring abundant common information between shared individual users. For the networks that cannot meet such requirements, social community structures actually provide complementary and critical information at a slightly coarse-grained level, alignment of which will provide additional information for user alignment. In turn, user alignment also reveals more clues for community alignment. Hence, in this paper, we introduce the problem of joint social network alignment, which aims to align users and communities across social networks simultaneously. Key challenges lie in that 1) how to learn the representations of both users and communities, and 2) how to make user alignment and community alignment benefit from each other. To address these challenges, we first elaborate on the characteristics of real-world networks with the notion of delta-hyperbolicity, and show the superiority of hyperbolic space for representing social networks. Then, we present a novel hyperbolic embedding approach for the joint social network alignment, referred to as PERFECT, in a unified optimization. Extensive experiments on real-world datasets show the superiority of PERFECT in both user alignment and community alignment.

cs.SI↗

arXiv2022

A Self-supervised Riemannian GNN with Time Varying Curvature for Temporal Graph Learning

Representation learning on temporal graphs has drawn considerable research attention owing to its fundamental importance in a wide spectrum of real-world applications. Though a number of studies succeed in obtaining time-dependent representations, it still faces significant challenges. On the one hand, most of the existing methods restrict the embedding space with a certain curvature. However, the underlying geometry in fact shifts among the positive curvature hyperspherical, zero curvature Euclidean and negative curvature hyperbolic spaces in the evolvement over time. On the other hand, these methods usually require abundant labels to learn temporal representations, and thereby notably limit their wide use in the unlabeled graphs of the real applications. To bridge this gap, we make the first attempt to study the problem of self-supervised temporal graph representation learning in the general Riemannian space, supporting the time-varying curvature to shift among hyperspherical, Euclidean and hyperbolic spaces. In this paper, we present a novel self-supervised Riemannian graph neural network (SelfRGNN). Specifically, we design a curvature-varying Riemannian GNN with a theoretically grounded time encoding, and formulate a functional curvature over time to model the evolvement shifting among the positive, zero and negative curvature spaces. To enable the self-supervised learning, we propose a novel reweighting self-contrastive approach, exploring the Riemannian space itself without augmentation, and propose an edge-based self-supervised curvature learning with the Ricci curvature. Extensive experiments show the superiority of SelfRGNN, and moreover, the case study shows the time-varying curvature of temporal graph in reality.

cs.LG↗

arXiv2022

CO(J = 1-0) Observations toward the Filamentary Cloud in the Galactic Region of $153.60^{\circ} \leqslant l \leqslant 156.50^{\circ}$ and $1.85^{\circ} \leqslant b \leqslant 3.50^{\circ}$

We present observations of $J$=1-0 transition lines of ${ }^{12} \mathrm{CO}$, ${ }^{13} \mathrm{CO}$, and $\mathrm{C}^{18} \mathrm{O}$ towards the Galactic region of $153.60^{\circ} \leqslant l \leqslant 156.50^{\circ}$ and $1.85^{\circ} \leqslant b \leqslant 3.50^{\circ}$, using the Purple Mountain Observatory (PMO) 13.7 m millimeter telescope. Based on the \tht data, one main filament and five sub-filaments are found together as a network structure in the velocity interval of $[-42.5, -30.0] \,\mathrm{km} \mathrm{\,s}^{-1}$. The kinematic distance of this molecular cloud (MC) is estimated to be $\sim4.5 \mathrm{\,kpc}$. The median length, width, excitation temperature, line mass of these filaments are $\sim49 \mathrm{\,pc}$, $\sim2.9 \mathrm{\,pc}$, $\sim8.9 \mathrm{\,K}$, and $\sim39 \,M_{\odot} \mathrm{pc}^{-1}$, respectively. The velocity structures along these filaments exhibit oscillatory patterns, which are likely caused by the fragmentation or accretion process along these filaments. The maximum accretion rate is estimated to be as high as $\sim700 \,M_{\odot} \mathrm{pc}^{-1}$. A total of $\sim162$ \tht clumps and $\sim 103$ young stellar objects (YSOs) are identified in this region. Most of the clumps are in gravitationally bound states. Three \hii regions (G154.359+2.606, SH2-211, SH2-212) are found to be located in the apexes of the filaments. Intense star forming activities are found along the entire filamentary cloud. The observed results may help us to better understand the link between filaments and massive star formation.

astro-ph.GA↗

arXiv2022

Cross Attention Based Style Distribution for Controllable Person Image Synthesis

Controllable person image synthesis task enables a wide range of applications through explicit control over body pose and appearance. In this paper, we propose a cross attention based style distribution module that computes between the source semantic styles and target pose for pose transfer. The module intentionally selects the style represented by each semantic and distributes them according to the target pose. The attention matrix in cross attention expresses the dynamic similarities between the target pose and the source styles for all semantics. Therefore, it can be utilized to route the color and texture from the source image, and is further constrained by the target parsing map to achieve a clearer objective. At the same time, to encode the source appearance accurately, the self attention among different semantic styles is also added. The effectiveness of our model is validated quantitatively and qualitatively on pose transfer and virtual try-on tasks.

cs.CV↗

arXiv2022

Federated Selective Aggregation for Knowledge Amalgamation

In this paper, we explore a new knowledge-amalgamation problem, termed Federated Selective Aggregation (FedSA). The goal of FedSA is to train a student model for a new task with the help of several decentralized teachers, whose pre-training tasks and data are different and agnostic. Our motivation for investigating such a problem setup stems from a recent dilemma of model sharing. Many researchers or institutes have spent enormous resources on training large and competent networks. Due to the privacy, security, or intellectual property issues, they are, however, not able to share their own pre-trained models, even if they wish to contribute to the community. The proposed FedSA offers a solution to this dilemma and makes it one step further since, again, the learned student may specialize in a new task different from all of the teachers. To this end, we proposed a dedicated strategy for handling FedSA. Specifically, our student-training process is driven by a novel saliency-based approach that adaptively selects teachers as the participants and integrates their representative capabilities into the student. To evaluate the effectiveness of FedSA, we conduct experiments on both single-task and multi-task settings. Experimental results demonstrate that FedSA effectively amalgamates knowledge from decentralized models and achieves competitive performance to centralized baselines.

cs.CV↗

arXiv2022

Context-aware Self-supervised Learning for Medical Images Using Graph Neural Network

Although self-supervised learning enables us to bootstrap the training by exploiting unlabeled data, the generic self-supervised methods for natural images do not sufficiently incorporate the context. For medical images, a desirable method should be sensitive enough to detect deviation from normal-appearing tissue of each anatomical region; here, anatomy is the context. We introduce a novel approach with two levels of self-supervised representation learning objectives: one on the regional anatomical level and another on the patient-level. We use graph neural networks to incorporate the relationship between different anatomical regions. The structure of the graph is informed by anatomical correspondences between each patient and an anatomical atlas. In addition, the graph representation has the advantage of handling any arbitrarily sized image in full resolution. Experiments on large-scale Computer Tomography (CT) datasets of lung images show that our approach compares favorably to baseline methods that do not account for the context. We use the learned embedding for staging lung tissue abnormalities related to COVID-19.

eess.IV↗

arXiv2022

Bootstrapping ViTs: Towards Liberating Vision Transformers from Pre-training

Recently, vision Transformers (ViTs) are developing rapidly and starting to challenge the domination of convolutional neural networks (CNNs) in the realm of computer vision (CV). With the general-purpose Transformer architecture replacing the hard-coded inductive biases of convolution, ViTs have surpassed CNNs, especially in data-sufficient circumstances. However, ViTs are prone to over-fit on small datasets and thus rely on large-scale pre-training, which expends enormous time. In this paper, we strive to liberate ViTs from pre-training by introducing CNNs' inductive biases back to ViTs while preserving their network architectures for higher upper bound and setting up more suitable optimization objectives. To begin with, an agent CNN is designed based on the given ViT with inductive biases. Then a bootstrapping training algorithm is proposed to jointly optimize the agent and ViT with weight sharing, during which the ViT learns inductive biases from the intermediate features of the agent. Extensive experiments on CIFAR-10/100 and ImageNet-1k with limited training data have shown encouraging results that the inductive biases help ViTs converge significantly faster and outperform conventional CNNs with even fewer parameters. Our code is publicly available at https://github.com/zhfeing/Bootstrapping-ViTs-pytorch.

cs.CV↗

arXiv2022

QS-Attn: Query-Selected Attention for Contrastive Learning in I2I Translation

Unpaired image-to-image (I2I) translation often requires to maximize the mutual information between the source and the translated images across different domains, which is critical for the generator to keep the source content and prevent it from unnecessary modifications. The self-supervised contrastive learning has already been successfully applied in the I2I. By constraining features from the same location to be closer than those from different ones, it implicitly ensures the result to take content from the source. However, previous work uses the features from random locations to impose the constraint, which may not be appropriate since some locations contain less information of source domain. Moreover, the feature itself does not reflect the relation with others. This paper deals with these problems by intentionally selecting significant anchor points for contrastive learning. We design a query-selected attention (QS-Attn) module, which compares feature distances in the source domain, giving an attention matrix with a probability distribution in each row. Then we select queries according to their measurement of significance, computed from the distribution. The selected ones are regarded as anchors for contrastive loss. At the same time, the reduced attention matrix is employed to route features in both domains, so that source relations maintain in the synthesis. We validate our proposed method in three different I2I datasets, showing that it increases the image quality without adding learnable parameters.

cs.CV↗

arXiv2022

Style Transformer for Image Inversion and Editing

Existing GAN inversion methods fail to provide latent codes for reliable reconstruction and flexible editing simultaneously. This paper presents a transformer-based image inversion and editing model for pretrained StyleGAN which is not only with less distortions, but also of high quality and flexibility for editing. The proposed model employs a CNN encoder to provide multi-scale image features as keys and values. Meanwhile it regards the style code to be determined for different layers of the generator as queries. It first initializes query tokens as learnable parameters and maps them into W+ space. Then the multi-stage alternate self- and cross-attention are utilized, updating queries with the purpose of inverting the input by the generator. Moreover, based on the inverted code, we investigate the reference- and label-based attribute editing through a pretrained latent classifier, and achieve flexible image-to-image translation with high quality results. Extensive experiments are carried out, showing better performances on both inversion and editing tasks within StyleGAN.

cs.CV↗

arXiv2022

3D ToF LiDAR in Mobile Robotics: A Review

In the past ten years, the use of 3D Time-of-Flight (ToF) LiDARs in mobile robotics has grown rapidly. Based on our accumulation of relevant research, this article systematically reviews and analyzes the use 3D ToF LiDARs in research and industrial applications. The former includes object detection, robot localization, long-term autonomy, LiDAR data processing under adverse weather conditions, and sensor fusion. The latter encompasses service robots, assisted and autonomous driving, and recent applications performed in response to public health crises. We hope that our efforts can effectively provide readers with relevant references and promote the deployment of existing mature technologies in real-world systems.

cs.RO↗

arXiv2021

Can contrastive learning avoid shortcut solutions?

The generalization of representations learned via contrastive learning depends crucially on what features of the data are extracted. However, we observe that the contrastive loss does not always sufficiently guide which features are extracted, a behavior that can negatively impact the performance on downstream tasks via "shortcuts", i.e., by inadvertently suppressing important predictive features. We find that feature extraction is influenced by the difficulty of the so-called instance discrimination task (i.e., the task of discriminating pairs of similar points from pairs of dissimilar ones). Although harder pairs improve the representation of some features, the improvement comes at the cost of suppressing previously well represented features. In response, we propose implicit feature modification (IFM), a method for altering positive and negative samples in order to guide contrastive models towards capturing a wider variety of predictive features. Empirically, we observe that IFM reduces feature suppression, and as a result improves performance on vision and medical imaging tasks. The code is available at: \url{https://github.com/joshr17/IFM}.

cs.LG↗

arXiv2021

A Self-supervised Mixed-curvature Graph Neural Network

Graph representation learning received increasing attentions in recent years. Most of existing methods ignore the complexity of the graph structures and restrict graphs in a single constant-curvature representation space, which is only suitable to particular kinds of graph structure indeed. Additionally, these methods follow the supervised or semi-supervised learning paradigm, and thereby notably limit their deployment on the unlabeled graphs in real applications. To address these aforementioned limitations, we take the first attempt to study the self-supervised graph representation learning in the mixed-curvature spaces. In this paper, we present a novel Self-supervised Mixed-curvature Graph Neural Network (SelfMGNN). Instead of working on one single constant-curvature space, we construct a mixed-curvature space via the Cartesian product of multiple Riemannian component spaces and design hierarchical attention mechanisms for learning and fusing the representations across these component spaces. To enable the self-supervisd learning, we propose a novel dual contrastive approach. The mixed-curvature Riemannian space actually provides multiple Riemannian views for the contrastive learning. We introduce a Riemannian projector to reveal these views, and utilize a well-designed Riemannian discriminator for the single-view and cross-view contrastive learning within and across the Riemannian views. Finally, extensive experiments show that SelfMGNN captures the complicated graph structures in reality and outperforms state-of-the-art baselines.

cs.LG↗

arXiv2021

Attribute-specific Control Units in StyleGAN for Fine-grained Image Manipulation

Image manipulation with StyleGAN has been an increasing concern in recent years.Recent works have achieved tremendous success in analyzing several semantic latent spaces to edit the attributes of the generated images.However, due to the limited semantic and spatial manipulation precision in these latent spaces, the existing endeavors are defeated in fine-grained StyleGAN image manipulation, i.e., local attribute translation.To address this issue, we discover attribute-specific control units, which consist of multiple channels of feature maps and modulation styles. Specifically, we collaboratively manipulate the modulation style channels and feature maps in control units rather than individual ones to obtain the semantic and spatial disentangled controls. Furthermore, we propose a simple yet effective method to detect the attribute-specific control units. We move the modulation style along a specific sparse direction vector and replace the filter-wise styles used to compute the feature maps to manipulate these control units. We evaluate our proposed method in various face attribute manipulation tasks. Extensive qualitative and quantitative results demonstrate that our proposed method performs favorably against the state-of-the-art methods. The manipulation results of real images further show the effectiveness of our method.

cs.CV↗

arXiv2021

Feedback from $γ$~Cassiopeiae: Large Expanding Cavity, Accelerating Cometary Globules, and Peculiar X-ray Emission

We present wide-field multi-wavelength observations of $γ$ Cassiopeiae (or $γ$~Cas for short) in order to study its feedback toward the interstellar environment. A large expanding cavity is discovered toward $γ$~Cas in the neutral hydrogen (HI) images at a systemic velocity of about -10 km/s. The measured dimension of the cavity is roughly 2.0 deg $\times$ 1.4 deg (or 6.0 pc $\times$ 4.2 pc at a distance of 168 pc), while the expansion velocity is about 5.0$\pm$0.5 km/s. The CO observations reveal systematic velocity gradients in IC63 (about 20 km/s/pc) and IC59 (about 30 km/s/pc), two cometary globules illuminated by $γ$~Cas, proving fast acceleration of the globules under stellar radiation pressure. The gas kinematics indicate that the cavity is opened by strong stellar wind, which has high potential to lead to the peculiar X-ray emission observed in $γ$~Cas. Our result favors a recent new scenario that emphasizes the roles of stellar wind and binarity in the X-ray emission of the $γ$~Cas stars.

astro-ph.SR↗

arXiv2021

Artificial Neural Network and Its Application Research Progress in Chemical Process

Most chemical processes, such as distillation, absorption, extraction, and catalytic reactions, are extremely complex processes that are affected by multiple factors. The relationships between their input variables and output variables are non-linear, and it is difficult to optimize or control them using traditional methods. Artificial neural network (ANN) is a systematic structure composed of multiple neuron models. Its main function is to simulate multiple basic functions of the nervous system of living organisms. ANN can achieve nonlinear control without relying on mathematical models, and is especially suitable for more complex control objects. This article will introduce the basic principles and development history of artificial neural networks, and review its application research progress in chemical process control, fault diagnosis, and process optimization.

eess.SY↗