arXiv subjects

Yi Jiang

Publications and source records attributed to Yi Jiang.

At least 181 records · Page 10Linked to original sources

arXiv2022

Highly in-plane anisotropic optical properties of fullerene monolayers

Both the intrinsic anisotropic optical materials and fullerene-assembled 2D materials have attracted a lot of interests in fundamental science and potential applications. The synthesis of a monolayer (ML) fullerene makes the combination of these two features plausible. In this work, using first-principles calculations, we systematically study the electronic structure, optical properties of quasi-hexagonal phase (qHP) ML and quasi-tetragonal phase (qTP) ML fullerenes. The calculations of qHP ML show that it is a semi-conductor with small anisotropic optical absorption, which agrees with the recent experimental measurements. However, the results for qTP ML reveal that it is a semimetal with highly in-plane anisotropic absorption. The dichroic ratio, namely the absorption ratio of $x$- and $y$-polarized light $α$$_x$$_x$/$α$$_y$$_y$, is around 12 at photon energy of 0.29 eV. This anisotropy is much more pronounced when the photon energy is between 0.7 and 1.4 eV, where $α$$_x$$_x$ becomes nearly zero while $α$$_y$$_y$ is more than two orders of magnitude larger. This indicates qTP ML as a candidate for long-pursuit lossless metal and a potential material for atomically thin polarizer. We hope this will stimulate further experimental efforts in the study of qTP ML and other fullerene-assembled 2D materials.

cond-mat.mtrl-sci↗

arXiv2022

SeqFormer: Sequential Transformer for Video Instance Segmentation

In this work, we present SeqFormer for video instance segmentation. SeqFormer follows the principle of vision transformer that models instance relationships among video frames. Nevertheless, we observe that a stand-alone instance query suffices for capturing a time sequence of instances in a video, but attention mechanisms shall be done with each frame independently. To achieve this, SeqFormer locates an instance in each frame and aggregates temporal information to learn a powerful representation of a video-level instance, which is used to predict the mask sequences on each frame dynamically. Instance tracking is achieved naturally without tracking branches or post-processing. On YouTube-VIS, SeqFormer achieves 47.4 AP with a ResNet-50 backbone and 49.0 AP with a ResNet-101 backbone without bells and whistles. Such achievement significantly exceeds the previous state-of-the-art performance by 4.6 and 4.4, respectively. In addition, integrated with the recently-proposed Swin transformer, SeqFormer achieves a much higher AP of 59.3. We hope SeqFormer could be a strong baseline that fosters future research in video instance segmentation, and in the meantime, advances this field with a more robust, accurate, neat model. The code is available at https://github.com/wjf5203/SeqFormer.

cs.CV↗

arXiv2022

In Defense of Online Models for Video Instance Segmentation

In recent years, video instance segmentation (VIS) has been largely advanced by offline models, while online models gradually attracted less attention possibly due to their inferior performance. However, online methods have their inherent advantage in handling long video sequences and ongoing videos while offline models fail due to the limit of computational resources. Therefore, it would be highly desirable if online models can achieve comparable or even better performance than offline models. By dissecting current online models and offline models, we demonstrate that the main cause of the performance gap is the error-prone association between frames caused by the similar appearance among different instances in the feature space. Observing this, we propose an online framework based on contrastive learning that is able to learn more discriminative instance embeddings for association and fully exploit history information for stability. Despite its simplicity, our method outperforms all online and offline methods on three benchmarks. Specifically, we achieve 49.5 AP on YouTube-VIS 2019, a significant improvement of 13.2 AP and 2.1 AP over the prior online and offline art, respectively. Moreover, we achieve 30.2 AP on OVIS, a more challenging dataset with significant crowding and occlusions, surpassing the prior art by 14.8 AP. The proposed method won first place in the video instance segmentation track of the 4th Large-scale Video Object Segmentation Challenge (CVPR2022). We hope the simplicity and effectiveness of our method, as well as our insight into current methods, could shed light on the exploration of VIS models.

cs.CV↗

arXiv2022

Multimodal Transformer with Variable-length Memory for Vision-and-Language Navigation

Vision-and-Language Navigation (VLN) is a task that an agent is required to follow a language instruction to navigate to the goal position, which relies on the ongoing interactions with the environment during moving. Recent Transformer-based VLN methods have made great progress benefiting from the direct connections between visual observations and the language instruction via the multimodal cross-attention mechanism. However, these methods usually represent temporal context as a fixed-length vector by using an LSTM decoder or using manually designed hidden states to build a recurrent Transformer. Considering a single fixed-length vector is often insufficient to capture long-term temporal context, in this paper, we introduce Multimodal Transformer with Variable-length Memory (MTVM) for visually-grounded natural language navigation by modelling the temporal context explicitly. Specifically, MTVM enables the agent to keep track of the navigation trajectory by directly storing previous activations in a memory bank. To further boost the performance, we propose a memory-aware consistency loss to help learn a better joint representation of temporal context with random masked instructions. We evaluate MTVM on popular R2R and CVDN datasets, and our model improves Success Rate on R2R unseen validation and test set by 2% each, and reduce Goal Process by 1.6m on CVDN test set.

cs.CV↗

arXiv2022

Physics-Inspired Unsupervised Classification for Region of Interest in X-Ray Ptychography

X-ray ptychography allows for large fields to be imaged at high resolution at the cost of additional computational expense due to the large volume of data. Given limited information regarding the object, the acquired data often has an excessive amount of information that is outside the region of interest (RoI). In this work we propose a physics-inspired unsupervised learning algorithm to identify the RoI of an object using only diffraction patterns from a ptychography dataset before committing computational resources to reconstruction. Obtained diffraction patterns that are automatically identified as not within the RoI are filtered out, allowing efficient reconstruction by focusing only on important data within the RoI while preserving image quality.

eess.IV↗

arXiv2022

DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion

A typical pipeline for multi-object tracking (MOT) is to use a detector for object localization, and following re-identification (re-ID) for object association. This pipeline is partially motivated by recent progress in both object detection and re-ID, and partially motivated by biases in existing tracking datasets, where most objects tend to have distinguishing appearance and re-ID models are sufficient for establishing associations. In response to such bias, we would like to re-emphasize that methods for multi-object tracking should also work when object appearance is not sufficiently discriminative. To this end, we propose a large-scale dataset for multi-human tracking, where humans have similar appearance, diverse motion and extreme articulation. As the dataset contains mostly group dancing videos, we name it "DanceTrack". We expect DanceTrack to provide a better platform to develop more MOT algorithms that rely less on visual discrimination and depend more on motion analysis. We benchmark several state-of-the-art trackers on our dataset and observe a significant performance drop on DanceTrack when compared against existing benchmarks. The dataset, project code and competition server are released at: \url{https://github.com/DanceTrack}.

cs.CV↗

arXiv2022

Two-dimensional Obstructed Atomic Insulators with Fractional Corner Charge in MA$_2$Z$_4$ Family

According to topological quantum chemistry, a class of electronic materials have been called obstructed atomic insulators (OAIs), in which a portion of valence electrons necessarily have their centers located on some empty $\textit{Wyckoff}$ positions without atoms occupation in the lattice. The obstruction of centering these electrons coinciding with their host atoms is nontrivial and results in metallic boundary states when the boundary is properly cut. Here, on basis of first-principles calculations in combination with topological quantum chemistry analysis, we propose two dimensional MA$_2$Z$_4$ (M = Cr, Mo and W; A = Si and Ge, Z = N, P and As) monolayer family are all OAIs. A typical case is the recently synthesized MoSi$_2$N$_4$. Although it is a topological trivial insulator with the occupied electronic states being integer combination of elementary band representations, it has valence electrons centering empty $\textit{Wyckoff}$ positions. It exhibits unique OAI-induced metallic edge states along the (1$\bar{1}$0) edge of MoSi$_2$N$_4$ monolayer and the in-gap corner states at three vertices of certain hexagonal nanodisk samples respecting C$_3$ rotation symmetry. The readily synthesized MoSi$_2$N$_4$ is quite stable and has a large bulk band gap of 1.94 eV, which makes the identification of these edge and corner states most possible for experimental clarification.

cond-mat.mtrl-sci↗

arXiv2022

Master integrals for mixed QCD-QED corrections to charged-current Drell-Yan production of a massive charged lepton

The master integrals for the mixed QCD-QED two-loop virtual corrections to the charged-current Drell-Yan process $q\bar{q}^{\prime} \rightarrow \ell ν$ are computed analytically by using the differential equation method. A suitable choice of master integrals makes it successful to cast the differential equation system into the canonical form. We keep the dependence on charged lepton mass in the building of differential equations and then expand the system against the ratio of small charged lepton mass to large $W$-boson mass. In such a way the final results will contain large logarithms of the form $\log(m_{\ell}^2/m_W^2)$. Finally, all the canonical master integrals are given as Taylor series around $d = 4$ spacetime dimensions up to order four, with coefficients expressed in terms of Goncharov polylogarithms up to weight four.

hep-ph↗

arXiv2022

Automatic Parameter Selection for Electron Ptychography via Bayesian Optimization

Electron ptychography provides new opportunities to resolve atomic structures with deep sub-angstrom spatial resolution and studying electron-beam sensitive materials with high dose efficiency. In practice, obtaining accurate ptychography images requires simultaneously optimizing multiple parameters that are often selected based on trial-and-error, resulting in low-throughput experiments and preventing wider adoption. Here, we develop an automatic parameter selection framework to circumvent this problem using Bayesian optimization with Gaussian processes. With minimal prior knowledge, the workflow efficiently produces ptychographic reconstructions that are superior than the ones processed by experienced experts. The method also facilitates better experimental designs by exploring optimized experimental parameters from simulated data.

cond-mat.mtrl-sci↗

arXiv2022

Nonlinear Kalman Filter Using Cramer Rao Bound

This paper studies the optimal state estimation for a dynamic system, whose transfer function can be nonlinear and the input noise can be of arbitrary distribution. Our algorithm differs from the conventional extended Kalman filter (EKF) and the particle filter (PF) in that it estimates not only the state vector but also the Cramer-Rao bound (CRB), which serves as an accuracy indicator. Combining the state estimation, the CRB, and the incoming new measurement, the algorithm updates the state estimation according to the maximum likelihood (ML) criterion. To illustrate the effectiveness of the proposed method for autonomous driving, we apply it to estimate the position and velocity of a vehicle based on the noisy measurements of distance and Doppler offset. Simulation results show that the proposed algorithm can achieve estimation significantly more accurate than the standard EKF and the PF.

eess.SP↗

arXiv2022

Constructions of Polyphase Golay Complementary Arrays

Golay complementary matrices (GCM) have recently drawn considerable attentions owing to its potential applications in omnidirectional precoding. In this paper we generalize the GCM to multi-dimensional Golay complementary arrays (GCA) and propose new constructions of GCA pairs and GCA quads. These constructions are facilitated by introducing a set of identities over a commutative ring. We prove that a quaternary GCA pair is feasible if the product of the array sizes in all dimensions is a quaternary Golay number with an additional constraint on the factorization of the product. For the binary GCM quads, we conjecture that the feasible sizes are arbitrary, and verify for sizes within 78 $\times$ 78 and other less densely distributed sizes. For the quaternary GCM quads, all the positive integers within 1000 can be covered for the size in one dimension.

eess.SP↗

arXiv2022

ByteTrack: Multi-Object Tracking by Associating Every Detection Box

Multi-object tracking (MOT) aims at estimating bounding boxes and identities of objects in videos. Most methods obtain identities by associating detection boxes whose scores are higher than a threshold. The objects with low detection scores, e.g. occluded objects, are simply thrown away, which brings non-negligible true object missing and fragmented trajectories. To solve this problem, we present a simple, effective and generic association method, tracking by associating almost every detection box instead of only the high score ones. For the low score detection boxes, we utilize their similarities with tracklets to recover true objects and filter out the background detections. When applied to 9 different state-of-the-art trackers, our method achieves consistent improvement on IDF1 score ranging from 1 to 10 points. To put forwards the state-of-the-art performance of MOT, we design a simple and strong tracker, named ByteTrack. For the first time, we achieve 80.3 MOTA, 77.3 IDF1 and 63.1 HOTA on the test set of MOT17 with 30 FPS running speed on a single V100 GPU. ByteTrack also achieves state-of-the-art performance on MOT20, HiEve and BDD100K tracking benchmarks. The source code, pre-trained models with deploy versions and tutorials of applying to other trackers are released at https://github.com/ifzhang/ByteTrack.

cs.CV↗

arXiv2022

Language as Queries for Referring Video Object Segmentation

Referring video object segmentation (R-VOS) is an emerging cross-modal task that aims to segment the target object referred by a language expression in all video frames. In this work, we propose a simple and unified framework built upon Transformer, termed ReferFormer. It views the language as queries and directly attends to the most relevant regions in the video frames. Concretely, we introduce a small set of object queries conditioned on the language as the input to the Transformer. In this manner, all the queries are obligated to find the referred objects only. They are eventually transformed into dynamic kernels which capture the crucial object-level information, and play the role of convolution filters to generate the segmentation masks from feature maps. The object tracking is achieved naturally by linking the corresponding queries across frames. This mechanism greatly simplifies the pipeline and the end-to-end framework is significantly different from the previous methods. Extensive experiments on Ref-Youtube-VOS, Ref-DAVIS17, A2D-Sentences and JHMDB-Sentences show the effectiveness of ReferFormer. On Ref-Youtube-VOS, Refer-Former achieves 55.6J&F with a ResNet-50 backbone without bells and whistles, which exceeds the previous state-of-the-art performance by 8.4 points. In addition, with the strong Swin-Large backbone, ReferFormer achieves the best J&F of 64.2 among all existing methods. Moreover, we show the impressive results of 55.0 mAP and 43.7 mAP on A2D-Sentences andJHMDB-Sentences respectively, which significantly outperforms the previous methods by a large margin. Code is publicly available at https://github.com/wjn922/ReferFormer.

cs.CV↗

arXiv2022

MetaFormer: A Unified Meta Framework for Fine-Grained Recognition

Fine-Grained Visual Classification(FGVC) is the task that requires recognizing the objects belonging to multiple subordinate categories of a super-category. Recent state-of-the-art methods usually design sophisticated learning pipelines to tackle this task. However, visual information alone is often not sufficient to accurately differentiate between fine-grained visual categories. Nowadays, the meta-information (e.g., spatio-temporal prior, attribute, and text description) usually appears along with the images. This inspires us to ask the question: Is it possible to use a unified and simple framework to utilize various meta-information to assist in fine-grained identification? To answer this problem, we explore a unified and strong meta-framework(MetaFormer) for fine-grained visual classification. In practice, MetaFormer provides a simple yet effective approach to address the joint learning of vision and various meta-information. Moreover, MetaFormer also provides a strong baseline for FGVC without bells and whistles. Extensive experiments demonstrate that MetaFormer can effectively use various meta-information to improve the performance of fine-grained recognition. In a fair comparison, MetaFormer can outperform the current SotA approaches with only vision information on the iNaturalist2017 and iNaturalist2018 datasets. Adding meta-information, MetaFormer can exceed the current SotA approaches by 5.9% and 5.3%, respectively. Moreover, MetaFormer can achieve 92.3% and 92.7% on CUB-200-2011 and NABirds, which significantly outperforms the SotA approaches. The source code and pre-trained models are released athttps://github.com/dqshuai/MetaFormer.

cs.CV↗

arXiv2022

Online Learning of Trellis Diagram Using Neural Network for Robust Detection and Decoding

This paper studies machine learning-assisted maximum likelihood (ML) and maximum a posteriori (MAP) receivers for a communication system with memory, which can be modelled by a trellis diagram. The prerequisite of the ML/MAP receiver is to obtain the likelihood of the received samples under different state transitions of the trellis diagram, which relies on the channel state information (CSI) and the distribution of the channel noise. We propose to learn the trellis diagram real-time using an artificial neural network (ANN) trained by a pilot sequence. This approach, termed as the online learning of trellis diagram (OLTD), requires neither the CSI nor statistics of the noise, and can be incorporated into the classic Viterbi and the BCJR algorithm. %Compared with the state-of-the-art ViterbiNet and BCJRNet algorithms in the literature, it It is shown to significantly outperform the model-based methods in non-Gaussian channels. It requires much less training overhead than the state-of-the-art methods, and hence is more feasible for real implementations. As an illustrative example, the OLTD-based BCJR is applied to a Bluetooth low energy (BLE) receiver trained only by a 256-sample pilot sequence. Moreover, the OLTD-based BCJR can accommodate for turbo equalization, while the state-of-the-art BCJRNet/ViterbiNet cannot. As an interesting by-product, we propose an enhancement to the BLE standard by introducing a bit interleaver to its physical layer; the resultant improvement of the receiver sensitivity can make it a better fit for some Internet of Things (IoT) communications.

eess.SP↗

arXiv2022

Channel Estimation and Projection for RIS-assisted MIMO Using Zadoff-Chu Sequences

The reconfigurable intelligent surface (RIS) technology is a promising enabler for millimeter wave (mmWave) wireless communications, as it can potentially provide spectral efficiency comparable to the conventional massive multiple-input multiple-output (MIMO) but with significantly lower hardware complexity. In this paper, we focus on the estimation and projection of the uplink RIS-aided massive MIMO channel, which can be time-varying. We propose to let the user equipments (UE) transmit Zadoff-Chu (ZC) sequences and let the base station (BS) conduct maximum likelihood (ML) estimation of the uplink channel. The proposed scheme is computationally efficient: it uses ZC sequences to decouple the estimation of the frequency and time offsets; it uses the space-alternating generalized expectation-maximization (SAGE) method to reduce the high-dimensional problem due to the multipaths to multiple lower-dimensional ones per path. Owing to the estimation of the Doppler frequency offsets, the time-varying channel state can be projected, which can significantly lower the overhead of the pilots for channel estimation. The numerical simulations verify the effectiveness of the proposed scheme.

cs.IT↗

arXiv2022

Objects in Semantic Topology

A more realistic object detection paradigm, Open-World Object Detection, has arisen increasing research interests in the community recently. A qualified open-world object detector can not only identify objects of known categories, but also discover unknown objects, and incrementally learn to categorize them when their annotations progressively arrive. Previous works rely on independent modules to recognize unknown categories and perform incremental learning, respectively. In this paper, we provide a unified perspective: Semantic Topology. During the life-long learning of an open-world object detector, all object instances from the same category are assigned to their corresponding pre-defined node in the semantic topology, including the `unknown' category. This constraint builds up discriminative feature representations and consistent relationships among objects, thus enabling the detector to distinguish unknown objects out of the known categories, as well as making learned features of known objects undistorted when learning new categories incrementally. Extensive experiments demonstrate that semantic topology, either randomly-generated or derived from a well-trained language model, could outperform the current state-of-the-art open-world object detectors by a large margin, e.g., the absolute open-set error is reduced from 7832 to 2546, exhibiting the inherent superiority of semantic topology on open-world object detection.

cs.CV↗

arXiv2022

Model-Based Neural Network and Its Application to Line Spectral Estimation

This paper presents the concept of "model-based neural network"(MNN), which is inspired by the classic artificial neural network (ANN) but for different usages. Instead of being used as a data-driven classifier, a MNN serves as a modeling tool with artfully defined inputs, outputs, and activation functions which have explicit physical meanings. Owing to the same layered form as an ANN, a MNN can also be optimized using the back-propagation (BP) algorithm. As an interesting application, the classic problem of line spectral estimation can be modeled by a MNN. We propose to first initialize the MNN by the fast Fourier transform (FFT) based spectral estimation, and then optimize the MNN by the BP algorithm, which automatically yields the maximum likelihood (ML) parameter estimation of the frequency spectrum. We also design a method of merging and pruning the hidden-layer nodes of the MNN, which can be used for model-order selection, i.e., to estimate the number of sinusoids. Numerical simulations verify the effectiveness of the proposed method.

eess.SP↗