arXiv subjects

Yuan He

Publications and source records attributed to Yuan He.

At least 145 records · Page 8Linked to original sources

arXiv2021

Hierarchical Similarity Learning for Language-based Product Image Retrieval

This paper aims for the language-based product image retrieval task. The majority of previous works have made significant progress by designing network structure, similarity measurement, and loss function. However, they typically perform vision-text matching at certain granularity regardless of the intrinsic multiple granularities of images. In this paper, we focus on the cross-modal similarity measurement, and propose a novel Hierarchical Similarity Learning (HSL) network. HSL first learns multi-level representations of input data by stacked encoders, and object-granularity similarity and image-granularity similarity are computed at each level. All the similarities are combined as the final hierarchical cross-modal similarity. Experiments on a large-scale product retrieval dataset demonstrate the effectiveness of our proposed method. Code and data are available at https://github.com/liufh1/hsl.

cs.CV↗

arXiv2021

Investigation of Factors Affecting Vertical Sag of Stretched Wire

To study vertical sag requirements and factors affecting the stretched wire alignment method, the vertical sag equation is first derived theoretically. Subsequently, the influencing factors,such as the hanging weight or tension, span length, temperature change, elastic deformation, and the Earths rotation, of the vertical sag are summarized, and their validity is verified through actual measurements. Finally, the essential factors affecting vertical sag, the specific strength and length, are discussed. It is believed that the vertical sag of a stretched wire is proportional to the square of the length and inversely proportional to the specific strength of the material.

physics.ins-det↗

arXiv2021

Fabrication and cold test of prototype of spatially periodic radio frequency quadrupole focusing linac

A 325 MHz aluminum prototype of a spatially periodic rf quadrupole focusing linac was developed at the Institute of Modern Physics, Chinese Academy of Sciences, as a promising candidate for the front end of a high-current linac. It consists of an alternating series of crossbar H-type drift tubes and rf quadrupole sections. Owing to its special geometry, cavity fabrication is a major hurdle for its engineering development and application. In this paper, we report the detailed mechanical design of this structure and describe its fabrication process, including machining, assembly, and inspection. The field distribution was measured by the bead-pull technique. The results show that the field errors of both the accelerating and focusing fields are within an acceptable range. A tuning scheme for this new structure is proposed and verified. The cold test process and results are presented in detail. The development of this prototype provides valuable guidance for the application of the spatially periodic rf quadrupole structure.

physics.acc-ph↗

arXiv2020

The Open Brands Dataset: Unified brand detection and recognition at scale

Intellectual property protection(IPP) have received more and more attention recently due to the development of the global e-commerce platforms. brand recognition plays a significant role in IPP. Recent studies for brand recognition and detection are based on small-scale datasets that are not comprehensive enough when exploring emerging deep learning techniques. Moreover, it is challenging to evaluate the true performance of brand detection methods in realistic and open scenes. In order to tackle these problems, we first define the special issues of brand detection and recognition compared with generic object detection. Second, a novel brands benchmark called "Open Brands" is established. The dataset contains 1,437,812 images which have brands and 50,000 images without any brand. The part with brands in Open Brands contains 3,113,828 instances annotated in 3 dimensions: 4 types, 559 brands and 1216 logos. To the best of our knowledge, it is the largest dataset for brand detection and recognition with rich annotations. We provide in-depth comprehensive statistics about the dataset, validate the quality of the annotations and study how the performance of many modern models evolves with an increasing amount of training data. Third, we design a network called "Brand Net" to handle brand recognition. Brand Net gets state-of-art mAP on Open Brand compared with existing detection methods.

cs.CV↗

arXiv2020

Composite Adversarial Attacks

Adversarial attack is a technique for deceiving Machine Learning (ML) models, which provides a way to evaluate the adversarial robustness. In practice, attack algorithms are artificially selected and tuned by human experts to break a ML system. However, manual selection of attackers tends to be sub-optimal, leading to a mistakenly assessment of model security. In this paper, a new procedure called Composite Adversarial Attack (CAA) is proposed for automatically searching the best combination of attack algorithms and their hyper-parameters from a candidate pool of \textbf{32 base attackers}. We design a search space where attack policy is represented as an attacking sequence, i.e., the output of the previous attacker is used as the initialization input for successors. Multi-objective NSGA-II genetic algorithm is adopted for finding the strongest attack policy with minimum complexity. The experimental result shows CAA beats 10 top attackers on 11 diverse defenses with less elapsed time (\textbf{6 $\times$ faster than AutoAttack}), and achieves the new state-of-the-art on $l_{\infty}$, $l_{2}$ and unrestricted adversarial attacks.

cs.CR↗

arXiv2020

Spiral wave chimeras in reaction-diffusion systems: phenomenon, mechanism and transitions

Spiral wave chimeras (SWCs), which combine the features of spiral waves and chimera states, are a new type of dynamical patterns emerged in spatiotemporal systems due to the spontaneous symmetry breaking of the system dynamics. In generating SWC, the conventional wisdom is that the dynamical elements should be coupled in a nonlocal fashion. For this reason, it is commonly believed that SWC is excluded from the general reaction-diffusion (RD) systems possessing only local couplings. Here, by an experimentally feasible model of three-component FitzHugh-Nagumo-type RD system, we demonstrate that, even though the system elements are locally coupled, stable SWCs can still be observed in a wide region in the parameter space. The properties of SWCs are explored, and the underlying mechanisms are analyzed from the point view of coupled oscillators. Transitions from SWC to incoherent states are also investigated, and it is found that SWCs are typically destabilized in two scenarios, namely core breakup and core expansion. The former is characterized by a continuous breakup of the single asynchronous core into a number of small asynchronous cores, whereas the latter is featured by the continuous expansion of the single asynchronous core to the whole space. Remarkably, in the scenario of core expansion, the system may develop into an intriguing state in which regular spiral waves are embedded in a completely disordered background. This state, which is named shadowed spirals, manifests from a new perspective the coexistence of incoherent and coherent states in spatiotemporal systems, generalizing therefore the traditional concept of chimera states. Our studies provide an affirmative answer to the observation of SWCs in RD systems, and pave a way to the realization of SWCs in experiments.

nlin.PS↗

arXiv2020

Heuristic Domain Adaptation

In visual domain adaptation (DA), separating the domain-specific characteristics from the domain-invariant representations is an ill-posed problem. Existing methods apply different kinds of priors or directly minimize the domain discrepancy to address this problem, which lack flexibility in handling real-world situations. Another research pipeline expresses the domain-specific information as a gradual transferring process, which tends to be suboptimal in accurately removing the domain-specific properties. In this paper, we address the modeling of domain-invariant and domain-specific information from the heuristic search perspective. We identify the characteristics in the existing representations that lead to larger domain discrepancy as the heuristic representations. With the guidance of heuristic representations, we formulate a principled framework of Heuristic Domain Adaptation (HDA) with well-founded theoretical guarantees. To perform HDA, the cosine similarity scores and independence measurements between domain-invariant and domain-specific representations are cast into the constraints at the initial and final states during the learning procedure. Similar to the final condition of heuristic search, we further derive a constraint enforcing the final range of heuristic network output to be small. Accordingly, we propose Heuristic Domain Adaptation Network (HDAN), which explicitly learns the domain-invariant and domain-specific representations with the above mentioned constraints. Extensive experiments show that HDAN has exceeded state-of-the-art on unsupervised DA, multi-source DA and semi-supervised DA. The code is available at https://github.com/cuishuhao/HDA.

cs.CV↗

arXiv2020

Multi-frequency Point Supported LLRF Front-end for CiADS Wide-bandwidth Application

The China initiative Accelerator Driven System, CiADS, physics design adopts $162.5 \,\mathrm{MHz}$, $325 \,\mathrm{MHz}$, and $650 \,\mathrm{MHz}$ cavities, which are driven by the corresponding radio frequency (RF) power system, requiring frequency translation front-end for the RF station. For that application, a general-purpose design front-end prototype has been developed to evaluate the multi-frequency point supported design feasibility. The difficult parts to achieve the requirements of the general-purpose design are reasonable device selection and balanced design. With a carefully selected low-noise wide-band RF mixer and amplifier to balance the performance of multi-frequency supported down-conversion, specially designed local oscillator (LO) distribution net to increase isolation between adjacent channels, and external band-pass filter to realize expected up-conversion frequencies, high maintenance and modular front-end general-purpose design has been implemented. Results of standard parameters show an $R^2$ value of at least $99.991\%$ in the range of $-60 \sim 10\,\mathrm{dBm}$ for linearity, up to $18\,\mathrm{dBm}$ for P1dB, and up to $89\,\mathrm{dBc}$ for crosstalk between adjacent channels. The phase noise spectrum is lower than $80\,\mathrm{dBc}$ in the range of $0 \sim 1\,\mathrm{MHz}$, and cumulative phase noise is $0.006^\circ$; amplitude and phase stability are $0.022\%$ and $0.034^\circ$, respectively.

physics.acc-ph↗

arXiv2020

Sharp Multiple Instance Learning for DeepFake Video Detection

With the rapid development of facial manipulation techniques, face forgery has received considerable attention in multimedia and computer vision community due to security concerns. Existing methods are mostly designed for single-frame detection trained with precise image-level labels or for video-level prediction by only modeling the inter-frame inconsistency, leaving potential high risks for DeepFake attackers. In this paper, we introduce a new problem of partial face attack in DeepFake video, where only video-level labels are provided but not all the faces in the fake videos are manipulated. We address this problem by multiple instance learning framework, treating faces and input video as instances and bag respectively. A sharp MIL (S-MIL) is proposed which builds direct mapping from instance embeddings to bag prediction, rather than from instance embeddings to instance prediction and then to bag prediction in traditional MIL. Theoretical analysis proves that the gradient vanishing in traditional MIL is relieved in S-MIL. To generate instances that can accurately incorporate the partially manipulated faces, spatial-temporal encoded instance is designed to fully model the intra-frame and inter-frame inconsistency, which further helps to promote the detection performance. We also construct a new dataset FFPMS for partially attacked DeepFake video detection, which can benefit the evaluation of different methods at both frame and video levels. Experiments on FFPMS and the widely used DFDC dataset verify that S-MIL is superior to other counterparts for partially attacked DeepFake video detection. In addition, S-MIL can also be adapted to traditional DeepFake image detection tasks and achieve state-of-the-art performance on single-frame datasets.

cs.CV↗

arXiv2020

GAP++: Learning to generate target-conditioned adversarial examples

Adversarial examples are perturbed inputs which can cause a serious threat for machine learning models. Finding these perturbations is such a hard task that we can only use the iterative methods to traverse. For computational efficiency, recent works use adversarial generative networks to model the distribution of both the universal or image-dependent perturbations directly. However, these methods generate perturbations only rely on input images. In this work, we propose a more general-purpose framework which infers target-conditioned perturbations dependent on both input image and target label. Different from previous single-target attack models, our model can conduct target-conditioned attacks by learning the relations of attack target and the semantics in image. Using extensive experiments on the datasets of MNIST and CIFAR10, we show that our method achieves superior performance with single target attack models and obtains high fooling rates with small perturbation norms.

cs.CV↗

arXiv2020

Energy-Efficient On-Chip Networks through Profiled Hybrid Switching

Virtual channel flow control is the de facto choice for modern networks-on-chip to allow better utilization of the link bandwidth through buffering and packet switching, which are also the sources of large power footprint and long per-hop latency. On the other hand, bandwidth can be plentiful for parallel workloads under virtual channel flow control. Thus, dated but simpler flow controls such as circuit switching can be utilized to improve the energy efficiency of modern networks-on-chip. In this paper, we propose to utilize part of the link bandwidth under circuit switching so that part of the traffic can be transmitted bufferlessly without routing. Our evaluations reveal that this proposal leads to a reduction of energy per flit by up to 32% while also provides very competitive latency per flit when compared to networks under virtual channel flow control.

cs.AR↗

arXiv2020

Robust Generative Adversarial Network

Generative adversarial networks (GANs) are powerful generative models, but usually suffer from instability and generalization problem which may lead to poor generations. Most existing works focus on stabilizing the training of the discriminator while ignoring the generalization properties. In this work, we aim to improve the generalization capability of GANs by promoting the local robustness within the small neighborhood of the training samples. We also prove that the robustness in small neighborhood of training sets can lead to better generalization. Particularly, we design a robust optimization framework where the generator and discriminator compete with each other in a \textit{worst-case} setting within a small Wasserstein ball. The generator tries to map \textit{the worst input distribution} (rather than a Gaussian distribution used in most GANs) to the real data distribution, while the discriminator attempts to distinguish the real and fake distribution \textit{with the worst perturbation}. We have proved that our robust method can obtain a tighter generalization upper bound than traditional GANs under mild assumptions, ensuring a theoretical superiority of RGAN over GANs. A series of experiments on CIFAR-10, STL-10 and CelebA datasets indicate that our proposed robust framework can improve on five baseline GAN models substantially and consistently.

cs.LG↗

arXiv2020

An Asynchronous Computability Theorem for Fair Adversaries

This paper proposes a simple topological characterization of a large class of fair adversarial models via affine tasks: sub-complexes of the second iteration of the standard chromatic subdivision. We show that the task computability of a model in the class is precisely captured by iterations of the corresponding affine task. Fair adversaries include, but are not restricted to, the models of wait-freedom, t-resilience, and $k$-concurrency. Our results generalize and improve all previously derived topological characterizations of the ability of a model to solve distributed tasks.

cs.DC↗

arXiv2020

Charge density wave and superconductivity in the family of telluride chalcogenides Zn1-xCuxIr2-yN(N = Al, Ti, Rh)yTe4

The interplay between superconductivity and charge density wave (CDW)/metal-to-insulator transition (MIT) has long been interested and studied in condensed matter physics. Here we study systematically the charge density wave and superconductivity properties in the solid solutions Zn1-xCuxIr2-yN(N = Al, Ti, Rh)yTe4. Resistivity, magnetic susceptibility and specific heat measurements indicate that the CDW state was suppressed immediately while the superconducting critical temperature (Tc) differs from each system. In the Al- and Ti-substitution cases, Tc increase as y increases and reaches a maximum around 2.75 K and 2.84 K respectively at y = 0.075, followed by a decrease of Tc before the chemical phase boundary is reached at y = 0.2. Nevertheless, Tc decreases monotonously with Rh-doping content y increases and disappears above 0.3 with measuring temperature down to 2 K. Surprisingly, in the Zn1-xCuxIr2Te4 solid solution, Tc enhances as x increases and reaches a maximum value of 2.82 K for x = 0.5 but subsequently survives over the whole doping range of 0.00 - 0.9 despite Tc changes slightly with higher doping content, which differs from the observation of zinc doping suppressing the superconductivity quickly in the high Tc cuprate superconductors. The specific heat anomaly at the superconducting transitions for the representative optimal doping samples are all slightly higher than the BCS value of 1.43 and indicate bulk superconductivity in these compounds. Finally, the CDW transition temperature (TCDW) and superconducting transition temperature (Tc) vs. x/y content phase diagrams of Zn1-xCuxIr2-yN(N = Al, Ti, Rh)yTe4 have been established and compared, which offers good opportunity to study the competition between CDW and superconductivity in the telluride chalcogenides.

cond-mat.supr-con↗

arXiv2020

Semantic Regularization: Improve Few-shot Image Classification by Reducing Meta Shift

Few-shot image classification requires the classifier to robustly cope with unseen classes even if there are only a few samples for each class. Recent advances benefit from the meta-learning process where episodic tasks are formed to train a model that can adapt to class change. However, these task sare independent to each other and existing works mainly rely on limited samples of individual support set in a single meta task. This strategy leads to severe meta shift issues across multiple tasks, meaning the learned prototypes or class descriptors are not stable as each task only involves their own support set. To avoid this problem, we propose a concise Semantic RegularizationNetwork to learn a common semantic space under the framework of meta-learning. In this space, all class descriptors can be regularized by the learned semantic basis, which can effectively solve the meta shift problem. The key is to train a class encoder and decoder structure that can encode the sample embedding features into the semantic domain with trained semantic basis, and generate a more stable and general class descriptor from the decoder. We evaluate our work by extensive comparisons with previous methods on three benchmark datasets (MiniImageNet, TieredImageNet, and CUB). The results show that the semantic regularization module improves performance by 4%-7% over the baseline method, and achieves competitive results over the current state-of-the-art models.

cs.CV↗

arXiv2020

Progressive Relation Learning for Group Activity Recognition

Group activities usually involve spatiotemporal dynamics among many interactive individuals, while only a few participants at several key frames essentially define the activity. Therefore, effectively modeling the group-relevant and suppressing the irrelevant actions (and interactions) are vital for group activity recognition. In this paper, we propose a novel method based on deep reinforcement learning to progressively refine the low-level features and high-level relations of group activities. Firstly, we construct a semantic relation graph (SRG) to explicitly model the relations among persons. Then, two agents adopting policy according to two Markov decision processes are applied to progressively refine the SRG. Specifically, one feature-distilling (FD) agent in the discrete action space refines the low-level spatio-temporal features by distilling the most informative frames. Another relation-gating (RG) agent in continuous action space adjusts the high-level semantic graph to pay more attention to group-relevant relations. The SRG, FD agent, and RG agent are optimized alternately to mutually boost the performance of each other. Extensive experiments on two widely used benchmarks demonstrate the effectiveness and superiority of the proposed approach.

cs.CV↗

arXiv2020

Machine Learning Empowered Beam Management for Intelligent Reflecting Surface Assisted MmWave Networks

Recently, intelligent reflecting surface (IRS) assisted mmWave networks are emerging, which bear the potential to address the blockage issue of the millimeter wave (mmWave) communication in a more cost-effective way. In particular, IRS is built by passive and programmable electromagnetic elements that can manipulate the mmWave propagation channel into a more favorable condition that is free of blockage via judicious joint BS-IRS transmission design. However, the coexistence of IRSs and mmWave BSs complicates the network architecture, and thus poses great challenges for efficient beam management (BM) that is one critical prerequisite for high performance mmWave networks. In this paper, we systematically evaluate the key issues and challenges of BM for IRS-assisted mmWave networks to bring insights into the future network design. Specifically, we carefully classify and discuss the extensibility and limitations of the existing BM of conventional mmWave towards the IRS-assisted new paradigm. Moreover, we propose a novel machine learning empowered BM framework for IRS-assisted networks with representative showcases, which processes environmental and mobility awareness to achieve highly efficient BM with significantly reduced system overhead. Finally, some interesting future directions are also suggested to inspire further researches.

eess.SP↗

arXiv2020

Fine-Grained Fashion Similarity Learning by Attribute-Specific Embedding Network

This paper strives to learn fine-grained fashion similarity. In this similarity paradigm, one should pay more attention to the similarity in terms of a specific design/attribute among fashion items, which has potential values in many fashion related applications such as fashion copyright protection. To this end, we propose an Attribute-Specific Embedding Network (ASEN) to jointly learn multiple attribute-specific embeddings in an end-to-end manner, thus measure the fine-grained similarity in the corresponding space. With two attention modules, i.e., Attribute-aware Spatial Attention and Attribute-aware Channel Attention, ASEN is able to locate the related regions and capture the essential patterns under the guidance of the specified attribute, thus make the learned attribute-specific embeddings better reflect the fine-grained similarity. Extensive experiments on four fashion-related datasets show the effectiveness of ASEN for fine-grained fashion similarity learning and its potential for fashion reranking.

cs.CV↗