Searcharxiv⌕ Search

arXiv subjects

Xu Yang

Publications and source records attributed to Xu Yang.

At least 307 records · Page 17Linked to original sources
arXiv2023

Unseen Object Instance Segmentation with Fully Test-time RGB-D Embeddings Adaptation

Segmenting unseen objects is a crucial ability for the robot since it may encounter new environments during the operation. Recently, a popular solution is leveraging RGB-D features of large-scale synthetic data and directly applying the model to unseen real-world scenarios. However, the domain shift caused by the sim2real gap is inevitable, posing a crucial challenge to the segmentation model. In this paper, we emphasize the adaptation process across sim2real domains and model it as a learning problem on the BatchNorm parameters of a simulation-trained model. Specifically, we propose a novel non-parametric entropy objective, which formulates the learning objective for the test-time adaptation in an open-world manner. Then, a cross-modality knowledge distillation objective is further designed to encourage the test-time knowledge transfer for feature enhancement. Our approach can be efficiently implemented with only test images, without requiring annotations or revisiting the large-scale synthetic training data. Besides significant time savings, the proposed method consistently improves segmentation results on the overlap and boundary metrics, achieving state-of-the-art performance on unseen object instance segmentation.

cs.CV↗
arXiv2023

An efficient material search for room temperature topological magnons

Topologically protected magnon surface states are highly desirable as an ideal platform to engineer low-dissipation spintronics devices. However, theoretical prediction of topological magnons in strongly correlated materials proves to be challenging because the ab initio density functional theory calculations fail to reliably predict magnetic interactions in correlated materials. Here, we present a symmetry-based approach, which predicts topological magnons in magnetically ordered crystals, upon applying external perturbations such as magnetic/electric fields and/or mechanical strains. We apply this approach to carry out an efficient search for magnetic materials in the Bilbao Crystallographic Server, where, among 198 compounds with an over 300-K transition temperature, we identify 12 magnetic insulators that support room-temperature topological magnons. They feature Weyl magnons with surface magnon arcs and magnon axion insulators with either chiral surface or hinge magnon modes, offering a route to realize energy-efficient devices based on protected surface magnons.

cond-mat.mtrl-sci↗
arXiv2023

On the Turán Number of Generalized Theta Graphs

Let $Θ_{k_1,\cdots,k_\ell}$ denote the generalized theta graph, which consists of $\ell$ internally disjoint paths with lengths $k_1,\cdots, k_{\ell}$, connecting two fixed vertices. We estimate the corresponding extremal number $\text{ex}(n,Θ_{k_1,\cdots,k_\ell})$. When the lengths of all paths have the same parity and at most one path has length 1, $\text{ex}(n,Θ_{k_1,\cdots,k_\ell})$ is $O(n^{1+1/k^\ast})$, where $2k^\ast$ is the length of the smallest cycle in $Θ_{k_1,\cdots,k_\ell}$. We also establish matching lower bound in the particular case of $\text{ex}(n,Θ_{3,5,5})$.

math.CO↗
arXiv2023

Data Release of the AST3-2 Automatic Survey from Dome A, Antarctica

AST3-2 is the second of the three Antarctic Survey Telescopes, aimed at wide-field time-domain optical astronomy. It is located at Dome A, Antarctica, which is by many measures the best optical astronomy site on the Earth's surface. Here we present the data from the AST3-2 automatic survey in 2016 and the photometry results. The median 5$σ$ limiting magnitude in $i$-band is 17.8 mag and the light curve precision is 4 mmag for bright stars. The data release includes photometry for over 7~million stars, from which over 3,500 variable stars were detected, with 70 of them newly discovered. We classify these new variables into different types by combining their light curve features with stellar properties from surveys such as StarHorse.

astro-ph.SR↗
arXiv2023

Seismic Tomography with Random Batch Gradient Reconstruction

Seismic tomography solves high-dimensional optimization problems to image subsurface structures of Earth. In this paper, we propose to use random batch methods to construct the gradient used for iterations in seismic tomography. Specifically, we use the frozen Gaussian approximation to compute seismic wave propagation, and then construct stochastic gradients by random batch methods. The method inherits the spirit of stochastic gradient descent methods for solving high-dimensional optimization problems. The proposed idea is general in the sense that it does not rely on the usage of the frozen Gaussian approximation, and one can replace it with any other efficient wave propagation solvers, e.g., Gaussian beam methods and spectral element methods. We prove the convergence of the random batch method in the mean-square sense, and show the numerical performance of the proposed method by two-dimensional and three-dimensional examples of wave-equation-based travel-time inversion and full-waveform inversion, respectively. As a byproduct, we also prove the convergence of the accelerated full-waveform inversion using dynamic mini-batches and spectral element methods.

math.NA↗
arXiv2022

Can AI detect pain and express pain empathy? A review from emotion recognition and a human-centered AI perspective

Sensory and emotional experiences such as pain and empathy are essential for mental and physical health. Cognitive neuroscience has been working on revealing mechanisms underlying pain and empathy. Furthermore, as trending research areas, computational pain recognition and empathic artificial intelligence (AI) show progress and promise for healthcare or human-computer interaction. Although AI research has recently made it increasingly possible to create artificial systems with affective processing, most cognitive neuroscience and AI research do not jointly address the issues of empathy in AI and cognitive neuroscience. The main aim of this paper is to introduce key advances, cognitive challenges and technical barriers in computational pain recognition and the implementation of artificial empathy. Our discussion covers the following topics: How can AI recognize pain from unimodal and multimodal information? Is it crucial for AI to be empathic? What are the benefits and challenges of empathic AI? Despite some consensus on the importance of AI, including empathic recognition and responses, we also highlight future challenges for artificial empathy and possible paths from interdisciplinary perspectives. Furthermore, we discuss challenges for responsible evaluation of cognitive methods and computational techniques and show approaches to future work to contribute to affective assistants capable of empathy.

cs.AI↗
arXiv2022

Image Projective Transformation Rectification with Synthetic Data for Smartphone-captured Chest X-ray Photos Classification

Classification on smartphone-captured chest X-ray (CXR) photos to detect pathologies is challenging due to the projective transformation caused by the non-ideal camera position. Recently, various rectification methods have been proposed for different photo rectification tasks such as document photos, license plate photos, etc. Unfortunately, we found that none of them is suitable for CXR photos, due to their specific transformation type, image appearance, annotation type, etc. In this paper, we propose an innovative deep learning-based Projective Transformation Rectification Network (PTRN) to automatically rectify CXR photos by predicting the projective transformation matrix. To the best of our knowledge, it is the first work to predict the projective transformation matrix as the learning goal for photo rectification. Additionally, to avoid the expensive collection of natural data, synthetic CXR photos are generated under the consideration of natural perturbations, extra screens, etc. We evaluate the proposed approach in the CheXphoto smartphone-captured CXR photos classification competition hosted by the Stanford University Machine Learning Group, our approach won first place with a huge performance improvement (ours 0.850, second-best 0.762, in AUC). A deeper study demonstrates that the use of PTRN successfully achieves the classification performance on the spatially transformed CXR photos to the same level as on the high-quality digital CXR images, indicating PTRN can eliminate all negative impacts of projective transformation on the CXR photos.

cs.CV↗
arXiv2022

Spikeformer: A Novel Architecture for Training High-Performance Low-Latency Spiking Neural Network

Spiking neural networks (SNNs) have made great progress on both performance and efficiency over the last few years,but their unique working pattern makes it hard to train a high-performance low-latency SNN.Thus the development of SNNs still lags behind traditional artificial neural networks (ANNs).To compensate this gap,many extraordinary works have been proposed.Nevertheless,these works are mainly based on the same kind of network structure (i.e.CNN) and their performance is worse than their ANN counterparts,which limits the applications of SNNs.To this end,we propose a novel Transformer-based SNN,termed "Spikeformer",which outperforms its ANN counterpart on both static dataset and neuromorphic dataset and may be an alternative architecture to CNN for training high-performance SNNs.First,to deal with the problem of "data hungry" and the unstable training period exhibited in the vanilla model,we design the Convolutional Tokenizer (CT) module,which improves the accuracy of the original model on DVS-Gesture by more than 16%.Besides,in order to better incorporate the attention mechanism inside Transformer and the spatio-temporal information inherent to SNN,we adopt spatio-temporal attention (STA) instead of spatial-wise or temporal-wise attention.With our proposed method,we achieve competitive or state-of-the-art (SOTA) SNN performance on DVS-CIFAR10,DVS-Gesture,and ImageNet datasets with the least simulation time steps (i.e.low latency).Remarkably,our Spikeformer outperforms other SNNs on ImageNet by a large margin (i.e.more than 5%) and even outperforms its ANN counterpart by 3.1% and 2.2% on DVS-Gesture and ImageNet respectively,indicating that Spikeformer is a promising architecture for training large-scale SNNs and may be more suitable for SNNs compared to CNN.We believe that this work shall keep the development of SNNs in step with ANNs as much as possible.Code will be available.

cs.NE↗
arXiv2022

Observations of pores and surrounding regions with CO 4.66 μm lines by BBSO/CYRA

Solar observations of carbon monoxide (CO) indicate the existence of lower-temperature gas in the lower solar chromosphere. We present an observation of pores, and quiet-Sun, and network magnetic field regions with CO 4.66 μm lines by the Cryogenic Infrared Spectrograph (CYRA) at Big Bear Solar Observatory. We used the strong CO lines at around 4.66 μm to understand the properties of the thermal structures of lower solar atmosphere in different solar features with various magnetic field strengths. AIA 1700 Å images, HMI continuum images and magnetograms are also included in the observation. The data from 3D radiation magnetohydrodynamic (MHD) simulation with the Bifrost code are also employed for the first time to be compared with the observation. We used the RH code to synthesize the CO line profiles in the network regions. The CO 3-2 R14 line center intensity changes to be either enhanced or diminished with increasing magnetic field strength, which should be caused by different heating effects in magnetic flux tubes with different sizes. We find several "cold bubbles" in the CO 3-2 R14 line center intensity images, which can be classified into two types. One type is located in the quiet-Sun regions without magnetic fields. The other type, which has rarely been reported in the past, is near or surrounded by magnetic fields. Notably, some are located at the edge of the magnetic network. The two kinds of cold bubbles and the relationship between cold bubble intensities and network magnetic field strength are both reproduced by the 3D MHD simulation with the Bifrost and RH codes. The simulation also shows that there is a cold plasma blob near the network magnetic fields, causing the observed cold bubbles seen in the CO 3-2 R14 line center image. Our observation and simulation illustrate that the magnetic field plays a vital role in the generation of some CO cold bubbles.

astro-ph.SR↗
arXiv2022

Auto-Encoding Score Distribution Regression for Action Quality Assessment

The action quality assessment (AQA) of videos is a challenging vision task since the relation between videos and action scores is difficult to model. Thus, AQA has been widely studied in the literature. Traditionally, AQA is treated as a regression problem to learn the underlying mappings between videos and action scores. But previous methods ignored data uncertainty in AQA dataset. To address aleatoric uncertainty, we further develop a plug-and-play module Distribution Auto-Encoder (DAE). Specifically, it encodes videos into distributions and uses the reparameterization trick in variational auto-encoders (VAE) to sample scores, which establishes a more accurate mapping between videos and scores. Meanwhile, a likelihood loss is used to learn the uncertainty parameters. We plug our DAE approach into MUSDL and CoRe. Experimental results on public datasets demonstrate that our method achieves state-of-the-art on AQA-7, MTL-AQA, and JIGSAWS datasets. Our code is available at https://github.com/InfoX-SEU/DAE-AQA.

cs.CV↗
arXiv2022

MemoNav: Selecting Informative Memories for Visual Navigation

Image-goal navigation is a challenging task, as it requires the agent to navigate to a target indicated by an image in a previously unseen scene. Current methods introduce diverse memory mechanisms which save navigation history to solve this task. However, these methods use all observations in the memory for generating navigation actions without considering which fraction of this memory is informative. To address this limitation, we present the MemoNav, a novel memory mechanism for image-goal navigation, which retains the agent's informative short-term memory and long-term memory to improve the navigation performance on a multi-goal task. The node features on the agent's topological map are stored in the short-term memory, as these features are dynamically updated. To aid the short-term memory, we also generate long-term memory by continuously aggregating the short-term memory via a graph attention module. The MemoNav retains the informative fraction of the short-term memory via a forgetting module based on a Transformer decoder and then incorporates this retained short-term memory and the long-term memory into working memory. Lastly, the agent uses the working memory for action generation. We evaluate our model on a new multi-goal navigation dataset. The experimental results show that the MemoNav outperforms the SoTA methods by a large margin with a smaller fraction of navigation history. The results also empirically show that our model is less likely to be trapped in a deadlock, which further validates that the MemoNav improves the agent's navigation efficiency by reducing redundant steps.

cs.CV↗
arXiv2022

Automatically Discovering Novel Visual Categories with Self-supervised Prototype Learning

This paper tackles the problem of novel category discovery (NCD), which aims to discriminate unknown categories in large-scale image collections. The NCD task is challenging due to the closeness to the real-world scenarios, where we have only encountered some partial classes and images. Unlike other works on the NCD, we leverage the prototypes to emphasize the importance of category discrimination and alleviate the issue of missing annotations of novel classes. Concretely, we propose a novel adaptive prototype learning method consisting of two main stages: prototypical representation learning and prototypical self-training. In the first stage, we obtain a robust feature extractor, which could serve for all images with base and novel categories. This ability of instance and category discrimination of the feature extractor is boosted by self-supervised learning and adaptive prototypes. In the second stage, we utilize the prototypes again to rectify offline pseudo labels and train a final parametric classifier for category clustering. We conduct extensive experiments on four benchmark datasets and demonstrate the effectiveness and robustness of the proposed method with state-of-the-art performance.

cs.CV↗
arXiv2022

Towards Unbiased Visual Emotion Recognition via Causal Intervention

Although much progress has been made in visual emotion recognition, researchers have realized that modern deep networks tend to exploit dataset characteristics to learn spurious statistical associations between the input and the target. Such dataset characteristics are usually treated as dataset bias, which damages the robustness and generalization performance of these recognition systems. In this work, we scrutinize this problem from the perspective of causal inference, where such dataset characteristic is termed as a confounder which misleads the system to learn the spurious correlation. To alleviate the negative effects brought by the dataset bias, we propose a novel Interventional Emotion Recognition Network (IERN) to achieve the backdoor adjustment, which is one fundamental deconfounding technique in causal inference. Specifically, IERN starts by disentangling the dataset-related context feature from the actual emotion feature, where the former forms the confounder. The emotion feature will then be forced to see each confounder stratum equally before being fed into the classifier. A series of designed tests validate the efficacy of IERN, and experiments on three emotion benchmarks demonstrate that IERN outperforms state-of-the-art approaches for unbiased visual emotion recognition. Code is available at https://github.com/donydchen/causal_emotion

cs.CV↗
arXiv2022

EMScore: Evaluating Video Captioning via Coarse-Grained and Fine-Grained Embedding Matching

Current metrics for video captioning are mostly based on the text-level comparison between reference and candidate captions. However, they have some insuperable drawbacks, e.g., they cannot handle videos without references, and they may result in biased evaluation due to the one-to-many nature of video-to-text and the neglect of visual relevance. From the human evaluator's viewpoint, a high-quality caption should be consistent with the provided video, but not necessarily be similar to the reference in literal or semantics. Inspired by human evaluation, we propose EMScore (Embedding Matching-based score), a novel reference-free metric for video captioning, which directly measures similarity between video and candidate captions. Benefit from the recent development of large-scale pre-training models, we exploit a well pre-trained vision-language model to extract visual and linguistic embeddings for computing EMScore. Specifically, EMScore combines matching scores of both coarse-grained (video and caption) and fine-grained (frames and words) levels, which takes the overall understanding and detailed characteristics of the video into account. Furthermore, considering the potential information gain, EMScore can be flexibly extended to the conditions where human-labeled references are available. Last but not least, we collect VATEX-EVAL and ActivityNet-FOIl datasets to systematically evaluate the existing metrics. VATEX-EVAL experiments demonstrate that EMScore has higher human correlation and lower reference dependency. ActivityNet-FOIL experiment verifies that EMScore can effectively identify "hallucinating" captions. The datasets will be released to facilitate the development of video captioning metrics. The code is available at: https://github.com/ShiYaya/emscore.

cs.CV↗
arXiv2022

Siamese Contrastive Embedding Network for Compositional Zero-Shot Learning

Compositional Zero-Shot Learning (CZSL) aims to recognize unseen compositions formed from seen state and object during training. Since the same state may be various in the visual appearance while entangled with different objects, CZSL is still a challenging task. Some methods recognize state and object with two trained classifiers, ignoring the impact of the interaction between object and state; the other methods try to learn the joint representation of the state-object compositions, leading to the domain gap between seen and unseen composition sets. In this paper, we propose a novel Siamese Contrastive Embedding Network (SCEN) (Code: https://github.com/XDUxyLi/SCEN-master) for unseen composition recognition. Considering the entanglement between state and object, we embed the visual feature into a Siamese Contrastive Space to capture prototypes of them separately, alleviating the interaction between state and object. In addition, we design a State Transition Module (STM) to increase the diversity of training compositions, improving the robustness of the recognition model. Extensive experiments indicate that our method significantly outperforms the state-of-the-art approaches on three challenging benchmark datasets, including the recent proposed C-QGA dataset.

cs.CV↗
arXiv2022

Chromospheric recurrent jets in a sunspot group and their inter-granular origin

We report on high resolution observations of recurrent fan-like jets by the Goode Solar telescope (GST) in multi-wavelengths inside a sunspot group. The dynamics behaviour of the jets is derived from the Ha line profiles. Quantitative values for one well-identified event have been obtained showing a maximum projected velocity of 42 km s^-1 and a Doppler shift of the order of 20 km s^-1. The footpoints/roots of the jets have a lifted center on the Ha line profile compared to the quiet sun suggesting a long lasting heating at these locations. The magnetic field between the small sunspots in the group shows a very high resolution pattern with parasitic polarities along the inter-granular lanes accompanied by high velocity converging flows (4 km s^-1) in the photosphere. Magnetic cancellations between the opposite polarities are observed in the vicinity of the footpoints of the jets. Along the inter-granular lanes horizontal magnetic field around 1000 Gauss is generated impulsively. Overall, all the kinetic features at the different layers through photosphere and chromosphere favor a convection-driven reconnection scenario for the recurrent fan-like jets, and evidence a site of reconnection between the photosphere and chromosphere corresponding to the inter-granular lanes.

astro-ph.SR↗
arXiv2022

A Distributed Implementation of Steady-State Kalman Filter

This paper studies the distributed state estimation in sensor network, where $m$ sensors are deployed to infer the $n$-dimensional state of a linear time-invariant (LTI) Gaussian system. By a lossless decomposition of optimal steady-state Kalman filter, we show that the problem of distributed estimation can be reformulated as synchronization of homogeneous linear systems. Based on such decomposition, a distributed estimator is proposed, where each sensor node runs a local filter using only its own measurement and fuses the local estimate of each node with a consensus algorithm. We show that the average of the estimate from all sensors coincides with the optimal Kalman estimate. Numerical examples are provided in the end to illustrate the performance of the proposed scheme.

eess.SY↗