arXiv subjects

Hao Chen

Publications and source records attributed to Hao Chen.

At least 1,135 records · Page 63Linked to original sources

arXiv2022

Unitail: Detecting, Reading, and Matching in Retail Scene

To make full use of computer vision technology in stores, it is required to consider the actual needs that fit the characteristics of the retail scene. Pursuing this goal, we introduce the United Retail Datasets (Unitail), a large-scale benchmark of basic visual tasks on products that challenges algorithms for detecting, reading, and matching. With 1.8M quadrilateral-shaped instances annotated, the Unitail offers a detection dataset to align product appearance better. Furthermore, it provides a gallery-style OCR dataset containing 1454 product categories, 30k text regions, and 21k transcriptions to enable robust reading on products and motivate enhanced product matching. Besides benchmarking the datasets using various state-of-the-arts, we customize a new detector for product detection and provide a simple OCR-based matching solution that verifies its effectiveness.

cs.CV↗

arXiv2022

CKD-TransBTS: Clinical Knowledge-Driven Hybrid Transformer with Modality-Correlated Cross-Attention for Brain Tumor Segmentation

Brain tumor segmentation (BTS) in magnetic resonance image (MRI) is crucial for brain tumor diagnosis, cancer management and research purposes. With the great success of the ten-year BraTS challenges as well as the advances of CNN and Transformer algorithms, a lot of outstanding BTS models have been proposed to tackle the difficulties of BTS in different technical aspects. However, existing studies hardly consider how to fuse the multi-modality images in a reasonable manner. In this paper, we leverage the clinical knowledge of how radiologists diagnose brain tumors from multiple MRI modalities and propose a clinical knowledge-driven brain tumor segmentation model, called CKD-TransBTS. Instead of directly concatenating all the modalities, we re-organize the input modalities by separating them into two groups according to the imaging principle of MRI. A dual-branch hybrid encoder with the proposed modality-correlated cross-attention block (MCCA) is designed to extract the multi-modality image features. The proposed model inherits the strengths from both Transformer and CNN with the local feature representation ability for precise lesion boundaries and long-range feature extraction for 3D volumetric images. To bridge the gap between Transformer and CNN features, we propose a Trans&CNN Feature Calibration block (TCFC) in the decoder. We compare the proposed model with five CNN-based models and six transformer-based models on the BraTS 2021 challenge dataset. Extensive experiments demonstrate that the proposed model achieves state-of-the-art brain tumor segmentation performance compared with all the competitors.

eess.IV↗

arXiv2022

60-nm-span wavelength-tunable vortex fiber laser with intracavity plasmon metasurfaces

Wavelength-tunable vortex fiber lasers that could generate beams carrying orbital angular momentum (OAM) hold great interest in large-capacity optical communications. The wavelength tunability of conventional vortex fiber lasers is however limited by the range of 35 nm due to narrow bandwidth and/or insertion loss of mode conversion components. Optical metasurfaces apart from being compact planar components can flexibly manipulate light with high efficiency in a broad wavelength range. Here, we propose and demonstrate for the first time, to the best of our knowledge, a metasurface-assisted vortex fiber laser that can directly generate OAM beams with changeable topological charges. Due to the designed broadband gap-surface plasmon metasurface, combined with an intracavity tunable filter, the laser enables OAM beam with center wavelength continuously tunable from 1015 nm to 1075 nm, nearly twice of other vortex fiber lasers ever reported. The metasurface can be designed at will to satisfy requirements for either low pump threshold or high slope efficiency of the laser. Furthermore, the cavity-metasurface configuration can be extended to generate higher-order OAM beams or more complex structured beams in different wavelength regions, which greatly broadens the possibilities for developing low-cost and high-quality structured-beam laser sources.

physics.optics↗

arXiv2022

Star Product PIR Schemes with Colluding Servers over Small Fields

Private Information Retrieval (PIR) was first proposed by B. Chor, O. Goldreich, E. Kushilevitz and M. Sudan in their 1995 FOCS paper. For MDS coded distributed storage system private information retrieval was proposed and the capacity of PIR schemes for MDS coded distributed storage was studied. Star product PIR schemes from general coded distributed storage system with colluding servers were constructed over general finite fields. These star product schemes has no restriction on the sizes of fields and can be constructed for coded distributed storage across large number of servers. In this paper we first propose and prove the Singleton type upper bound on the storage rate, ratio of colluding servers and the retrieval rate of the star product PIR schemes. Secondly star product PIR schemes for coded distributed storage from algebraic geometry (AG) codes are analysed. We prove that when the number of the servers goes to the infinity, star product PIR schemes with colluding servers for AG-coded distributed storage have parameters closing to the Singleton type upper bound if the field is large. Comparing with the star product PIR schemes for Reed-Solomon coded and Reed-Muller coded distributed storage we show that PIR schemes with colluding servers for AG coded distributed storage have their performance advantages. AG-code based star product PIR schemes with colluding, Byzantine and unresponsive servers are discussed. $q$-ary cyclic code based star product PIR schemes for replicated data storage are also studied. When the storage code is the Reed-Muller code, the best choice of the retrieval code is not always the Reed-Muller code.

cs.IT↗

arXiv2022

Non-Gaussianities in Collider Energy Flux

The microscopic dynamics of particle collisions is imprinted into the statistical properties of asymptotic energy flux, much like the dynamics of inflation is imprinted into the cosmic microwave background. This energy flux is characterized by correlation functions $\langle \mathcal{E}(\vec n_1)\cdots \mathcal{E}(\vec n_k) \rangle$ of energy flow operators $ \mathcal{E}(\vec n)$. There has been significant recent progress in studying energy flux, including the calculation of multi-point correlation functions and their direct measurement inside high-energy jets at the Large Hadron Collider (LHC). In this paper, we build on these advances by defining a notion of "celestial non-gaussianity" as a ratio of the three-point function to a product of two-point functions. We show that this celestial non-gaussianity is under perturbative control within jets at the LHC, allowing us to cleanly access the non-gaussian interactions of quarks and gluons. We find good agreement between perturbative calculations of the non-gaussianity and a charged-particle-based analysis using CMS Open Data, and we observe a strong non-gaussianity peaked in the "flattened triangle" regime. The ability to robustly study three-point correlations is a significant step in advancing our understanding of jet substructure at the LHC. We anticipate that the celestial non-gaussianity, and its generalizations, will play an important role in the development of higher-order parton showers simulations and in the hunt for ever more subtle signals of potential new physics within jets.

hep-ph↗

arXiv2022

ORF-Net: Deep Omni-supervised Rib Fracture Detection from Chest CT Scans

Most of the existing object detection works are based on the bounding box annotation: each object has a precise annotated box. However, for rib fractures, the bounding box annotation is very labor-intensive and time-consuming because radiologists need to investigate and annotate the rib fractures on a slice-by-slice basis. Although a few studies have proposed weakly-supervised methods or semi-supervised methods, they could not handle different forms of supervision simultaneously. In this paper, we proposed a novel omni-supervised object detection network, which can exploit multiple different forms of annotated data to further improve the detection performance. Specifically, the proposed network contains an omni-supervised detection head, in which each form of annotation data corresponds to a unique classification branch. Furthermore, we proposed a dynamic label assignment strategy for different annotated forms of data to facilitate better learning for each branch. Moreover, we also design a confidence-aware classification loss to emphasize the samples with high confidence and further improve the model's performance. Extensive experiments conducted on the testing dataset show our proposed method outperforms other state-of-the-art approaches consistently, demonstrating the efficacy of deep omni-supervised learning on improving rib fracture detection performance.

cs.CV↗

arXiv2022

An Intermediate-level Attack Framework on The Basis of Linear Regression

This paper substantially extends our work published at ECCV, in which an intermediate-level attack was proposed to improve the transferability of some baseline adversarial examples. Specifically, we advocate a framework in which a direct linear mapping from the intermediate-level discrepancies (between adversarial features and benign features) to prediction loss of the adversarial example is established. By delving deep into the core components of such a framework, we show that 1) a variety of linear regression models can all be considered in order to establish the mapping, 2) the magnitude of the finally obtained intermediate-level adversarial discrepancy is correlated with the transferability, 3) further boost of the performance can be achieved by performing multiple runs of the baseline attack with random initialization. In addition, by leveraging these findings, we achieve new state-of-the-arts on transfer-based $\ell_\infty$ and $\ell_2$ attacks. Our code is publicly available at https://github.com/qizhangli/ila-plus-plus-lr.

cs.CV↗

arXiv2022

InsMix: Towards Realistic Generative Data Augmentation for Nuclei Instance Segmentation

Nuclei Segmentation from histology images is a fundamental task in digital pathology analysis. However, deep-learning-based nuclei segmentation methods often suffer from limited annotations. This paper proposes a realistic data augmentation method for nuclei segmentation, named InsMix, that follows a Copy-Paste-Smooth principle and performs morphology-constrained generative instance augmentation. Specifically, we propose morphology constraints that enable the augmented images to acquire luxuriant information about nuclei while maintaining their morphology characteristics (e.g., geometry and location). To fully exploit the pixel redundancy of the background and improve the model's robustness, we further propose a background perturbation method, which randomly shuffles the background patches without disordering the original nuclei distribution. To achieve contextual consistency between original and template instances, a smooth-GAN is designed with a foreground similarity encoder (FSE) and a triplet loss. We validated the proposed method on two datasets, i.e., Kumar and CPS datasets. Experimental results demonstrate the effectiveness of each component and the superior performance achieved by our method to the state-of-the-art methods.

eess.IV↗

arXiv2022

Dual-Distribution Discrepancy for Anomaly Detection in Chest X-Rays

Chest X-ray (CXR) is the most typical radiological exam for diagnosis of various diseases. Due to the expensive and time-consuming annotations, detecting anomalies in CXRs in an unsupervised fashion is very promising. However, almost all of the existing methods consider anomaly detection as a one-class classification (OCC) problem. They model the distribution of only known normal images during training and identify the samples not conforming to normal profile as anomalies in the testing phase. A large number of unlabeled images containing anomalies are thus ignored in the training phase, although they are easy to obtain in clinical practice. In this paper, we propose a novel strategy, Dual-distribution Discrepancy for Anomaly Detection (DDAD), utilizing both known normal images and unlabeled images. The proposed method consists of two modules. During training, one module takes both known normal and unlabeled images as inputs, capturing anomalous features from unlabeled images in some way, while the other one models the distribution of only known normal images. Subsequently, inter-discrepancy between the two modules, and intra-discrepancy inside the module that is trained on only normal images are designed as anomaly scores to indicate anomalies. Experiments on three CXR datasets demonstrate that the proposed DDAD achieves consistent, significant gains and outperforms state-of-the-art methods. Code is available at https://github.com/caiyu6666/DDAD.

eess.IV↗

arXiv2022

Quantum corrections to the quasinormal modes of the Schwarzschild black hole

Based on the minimum measurable momentum concepts associated with the quantum gravity effects acting on the large-scale dynamics of the universe, we study the quantum effect of the EUP on the Hawking evaporation of the black hole. The results show the quantum corrections may shorten the lifetime of the massive black hole. To verify the new EUP on the black hole stability, the scalar field and electromagnetic field are derived and the time evolution of the black hole is analyzed in terms of the time domain integration method, the quantum effect alters the oscillation and decay time of black hole. Furthermore, we use the WKB numerical approximation method to calculate the quasinormal mode frequencies and analyze the influence of the EUP parameter $α$ on the scattering problem. This shows that the EUP significantly increases the area of the total absorption cross-section of the black hole.

gr-qc↗

arXiv2022

Linear MSRD codes with Various Matrix Sizes and Unrestricted Lengths

A sum-rank-metric code attaining the Singleton bound is called maximum sum-rank distance (MSRD). MSRD codes have been constructed for some parameter cases. In this paper we construct a linear MSRD code over an arbitrary field ${\bf F}_q$ with various matrix sizes $n_1>n_2>\cdots>n_t$ satisfying $n_i \geq n_{i+1}^2+\cdots+n_t^2$ for $i=1, 2, \ldots, t-1$ for any given minimum sum-rank distance.

cs.IT↗

arXiv2022

Federated Spatial Reuse Optimization in Next-Generation Decentralized IEEE 802.11 WLANs

As wireless standards evolve, more complex functionalities are introduced to address the increasing requirements in terms of throughput, latency, security, and efficiency. To unleash the potential of such new features, artificial intelligence (AI) and machine learning (ML) are currently being exploited for deriving models and protocols from data, rather than by hand-programming. In this paper, we explore the feasibility of applying ML in next-generation wireless local area networks (WLANs). More specifically, we focus on the IEEE 802.11ax spatial reuse (SR) problem and predict its performance through federated learning (FL) models. The set of FL solutions overviewed in this work is part of the 2021 International Telecommunication Union (ITU) AI for 5G Challenge.

cs.NI↗

arXiv2022

RACA: Relation-Aware Credit Assignment for Ad-Hoc Cooperation in Multi-Agent Deep Reinforcement Learning

In recent years, reinforcement learning has faced several challenges in the multi-agent domain, such as the credit assignment issue. Value function factorization emerges as a promising way to handle the credit assignment issue under the centralized training with decentralized execution (CTDE) paradigm. However, existing value function factorization methods cannot deal with ad-hoc cooperation, that is, adapting to new configurations of teammates at test time. Specifically, these methods do not explicitly utilize the relationship between agents and cannot adapt to different sizes of inputs. To address these limitations, we propose a novel method, called Relation-Aware Credit Assignment (RACA), which achieves zero-shot generalization in ad-hoc cooperation scenarios. RACA takes advantage of a graph-based relation encoder to encode the topological structure between agents. Furthermore, RACA utilizes an attention-based observation abstraction mechanism that can generalize to an arbitrary number of teammates with a fixed number of parameters. Experiments demonstrate that our method outperforms baseline methods on the StarCraftII micromanagement benchmark and ad-hoc cooperation scenarios.

cs.LG↗

arXiv2022

BiC-Net: Learning Efficient Spatio-Temporal Relation for Text-Video Retrieval

The task of text-video retrieval aims to understand the correspondence between language and vision, has gained increasing attention in recent years. Previous studies either adopt off-the-shelf 2D/3D-CNN and then use average/max pooling to directly capture spatial features with aggregated temporal information as global video embeddings, or introduce graph-based models and expert knowledge to learn local spatial-temporal relations. However, the existing methods have two limitations: 1) The global video representations learn video temporal information in a simple average/max pooling manner and do not fully explore the temporal information between every two frames. 2) The graph-based local video representations are handcrafted, it depends heavily on expert knowledge and empirical feedback, which may not be able to effectively mine the higher-level fine-grained visual relations. These limitations result in their inability to distinguish videos with the same visual components but with different relations. To solve this problem, we propose a novel cross-modal retrieval framework, Bi-Branch Complementary Network (BiC-Net), which modifies transformer architecture to effectively bridge text-video modalities in a complementary manner via combining local spatial-temporal relation and global temporal information. Specifically, local video representations are encoded using multiple transformer blocks and additional residual blocks to learn spatio-temporal relation features, calling the module a Spatio-Temporal Residual transformer (SRT). Meanwhile, Global video representations are encoded using a multi-layer transformer block to learn global temporal features. Finally, we align the spatio-temporal relation and global temporal features with the text feature on two embedding spaces for cross-modal text-video retrieval.

cs.CV↗

arXiv2022

Lower and Upper Bounds for Numbers of Linear Regions of Graph Convolutional Networks

The research for characterizing GNN expressiveness attracts much attention as graph neural networks achieve a champion in the last five years. The number of linear regions has been considered a good measure for the expressivity of neural networks with piecewise linear activation. In this paper, we present some estimates for the number of linear regions of the classic graph convolutional networks (GCNs) with one layer and multiple-layer scenarios. In particular, we obtain an optimal upper bound for the maximum number of linear regions for one-layer GCNs, and the upper and lower bounds for multi-layer GCNs. The simulated estimate shows that the true maximum number of linear regions is possibly closer to our estimated lower bound. These results imply that the number of linear regions of multi-layer GCNs is exponentially greater than one-layer GCNs per parameter in general. This suggests that deeper GCNs have more expressivity than shallow GCNs.

cs.LG↗

arXiv2022

Strict Half-Singleton Bound, Strict Direct Upper Bound for Linear Insertion-Deletion Codes and Optimal Codes

Insertion-deletion codes (insdel codes for short) are used for correcting synchronization errors in communications, and in other many interesting fields such as DNA storage, date analysis, race-track memory error correction and language processing, and have recently gained a lot of attention. To determine the insdel distances of linear codes is a very challenging problem. The half-Singleton bound on the insdel distances of linear codes due to Cheng-Guruswami-Haeupler-Li is a basic upper bound on the insertion-deletion error-correcting capabilities of linear codes. On the other hand the natural direct upper bound $d_I(\mathcal C) \leq 2d_H(\mathcal C)$ is valid for any insdel code. In this paper, for a linear insdel code $\mathcal C$ we propose a strict half-Singleton upper bound $d_I(\mathcal C) \leq 2(n-2k+1)$ if $\mathcal C$ does not contain the codeword with all 1s, and a stronger direct upper bound $d_I(\mathcal C) \leq 2(d_H(\mathcal C)-t)$ under a weak condition, where $t\geq 1$ is a positive integer determined by the generator matrix. We also give optimal linear insdel codes attaining our strict half-Singleton bound and direct upper bound, and show that the code length of optimal binary linear insdel codes with respect to the (strict) half-Singleton bound is about twice the dimension. Interestingly explicit optimal linear insdel codes attaining the (strict) half-Singleton bound, with the code length being independent of the finite field size, are given.

cs.IT↗

arXiv2022

Tensor Network States with Low-Rank Tensors

Tensor networks are used to efficiently approximate states of strongly-correlated quantum many-body systems. More generally, tensor network approximations may allow to reduce the costs for operating on an order-$N$ tensor from exponential to polynomial in $N$, and this has become a popular approach for machine learning. We introduce the idea of imposing low-rank constraints on the tensors that compose the tensor network. With this modification, the time and space complexities for the network optimization can be substantially reduced while maintaining high accuracy. We detail this idea for tree tensor network states (TTNS) and projected entangled-pair states. Simulations of spin models on Cayley trees with low-rank TTNS exemplify the effect of rank constraints on the expressive power. We find that choosing the tensor rank $r$ to be on the order of the bond dimension $m$, is sufficient to obtain high-accuracy groundstate approximations and to substantially outperform standard TTNS computations. Thus low-rank tensor networks are a promising route for the simulation of quantum matter and machine learning on large data sets.

cond-mat.str-el↗

arXiv2022

List-decodable Codes and Covering Codes

The list-decodable code has been an active topic in theoretical computer science.There are general results about the list-decodability to the Johnson radius and the list-decoding capacity theorem. In this paper we show that rates, list-decodable radius and list sizes are closely related to the classical topic of covering codes. We prove new general simple but strong upper bounds for list-decodable codes in general finite metric spaces based on various covering codes. The general covering code upper bounds can be applied to the case that the volumes of the balls depend on the centers, not only on the radius. Then any good upper bound on the covering radius or the size of covering code imply a good upper bound on the sizes of list-decodable codes. Our results give exponential improvements on the recent generalized Singleton upper bound in STOC 2020 for Hamming metric list-decodable codes, when the code lengths are large. A generalized Singleton upper bound for average-radius list-decodable codes is also given from our general covering code upper bound. We also suggest to study the combinatorial covering list-decodable codes as a natural generalization of combinatorial list-decodable codes. We apply our general covering code upper bounds for list-decodable rank-metric codes, list-decodable subspace codes, list-decodable insertion codes list-decodable deletion codes,list-decodable sum-rank-metric codes and list decodable permutation codes. Some new better results about non-list-decodability of rank-metric codes, subspace codes, sum-rank-metric codes and permutation codes with various metrics are obtained.

cs.IT↗