arXiv subjects

Yi Jin

Publications and source records attributed to Yi Jin.

At least 73 records · Page 4Linked to original sources

arXiv2023

NPS: A Framework for Accurate Program Sampling Using Graph Neural Network

With the end of Moore's Law, there is a growing demand for rapid architectural innovations in modern processors, such as RISC-V custom extensions, to continue performance scaling. Program sampling is a crucial step in microprocessor design, as it selects representative simulation points for workload simulation. While SimPoint has been the de-facto approach for decades, its limited expressiveness with Basic Block Vector (BBV) requires time-consuming human tuning, often taking months, which impedes fast innovation and agile hardware development. This paper introduces Neural Program Sampling (NPS), a novel framework that learns execution embeddings using dynamic snapshots of a Graph Neural Network. NPS deploys AssemblyNet for embedding generation, leveraging an application's code structures and runtime states. AssemblyNet serves as NPS's graph model and neural architecture, capturing a program's behavior in aspects such as data computation, code path, and data flow. AssemblyNet is trained with a data prefetch task that predicts consecutive memory addresses. In the experiments, NPS outperforms SimPoint by up to 63%, reducing the average error by 38%. Additionally, NPS demonstrates strong robustness with increased accuracy, reducing the expensive accuracy tuning overhead. Furthermore, NPS shows higher accuracy and generality than the state-of-the-art GNN approach in code behavior learning, enabling the generation of high-quality execution embeddings.

cs.AR↗

arXiv2022

Shinning Light on Sterile Neutrino Portal Dark Matter from Cosmology and Collider

Provided the dark sector consisted of a dark scalar $ϕ$ and a dark fermion $χ$ under an exact $Z_2$ symmetry, the sterile neutrino $N$ can act as the messenger between the dark sector and standard model via the Yukawa coupling $λ_{ds} \barχϕN$. In this paper, we focus on the specific scenario $m_N>m_ϕ+m_χ$ with $χ$ being a FIMP dark matter. The decay width of dark scalar $ϕ$ is doubly suppressed by the smallness of Yukawa coupling $λ_{ds}$ and mixing angle $θ$. The delayed decay $ϕ\toχν$ will have a great impact on cosmological observables such as the Big Bang Nucleosynthesis, the Cosmic Microwave Background anisotropy power spectra, the effective number of relativistic neutrino species $N_{\rm eff}$ and the energetic neutrino flux. Meanwhile, the sterile neutrino can generate displaced vertex signature at colliders when $m_N<m_W$. The dark scalar $ϕ$ will also induce measurable Higgs invisible decay for relatively large quartic coupling. A comprehensive analysis of constraints from cosmology and collider is performed in this paper. We find that almost the whole parameter space with $m_N<m_W$ is under the reach of future experiments.

hep-ph↗

arXiv2022

Unraveling the Scotogenic Model at Muon Collider

The Scotogenic model extends the standard model with three singlet fermion $N_i$ and one inert doublet scalar $η$ to address the common origin of tiny neutrino mass and dark matter. For fermion dark matter $N_1$, a hierarchical Yukawa structure $|y_{1e}|\ll|y_{1μ}|\sim|y_{1τ}|\sim\mathcal{O}(1)$ is usually favored to satisfy constraints from lepton flavor violation and relic density. Such large $μ$-related Yukawa coupling would greatly enhance the pair production of charged scalar $η^\pm$ at the muon collider. In this paper, we investigate the dilepton signature of the Scotogenic model at a 14 TeV muon collider. For the dimuon signature $μ^+μ^-+/ \hspace{-0.65em} E_T$, we find that most viable samples can be probed with $200~\text{fb}^{-1}$ data. The ditau signature $τ^+τ^-+/ \hspace{-0.65em}E_T$ is usually less promising but is important to probe the small $|y_{1μ}|$ region. The mono-photon signature $γ+/ \hspace{-0.65em} E_T$ could also probe the compressed mass region $M_1\lesssim M_{η^\pm}$. Masses of charged scalar $η^\pm$ and dark matter $N_1$ can be further extracted by a binned likelihood fit of the dilepton energy.

hep-ph↗

arXiv2022

Deliberated Domain Bridging for Domain Adaptive Semantic Segmentation

In unsupervised domain adaptation (UDA), directly adapting from the source to the target domain usually suffers significant discrepancies and leads to insufficient alignment. Thus, many UDA works attempt to vanish the domain gap gradually and softly via various intermediate spaces, dubbed domain bridging (DB). However, for dense prediction tasks such as domain adaptive semantic segmentation (DASS), existing solutions have mostly relied on rough style transfer and how to elegantly bridge domains is still under-explored. In this work, we resort to data mixing to establish a deliberated domain bridging (DDB) for DASS, through which the joint distributions of source and target domains are aligned and interacted with each in the intermediate space. At the heart of DDB lies a dual-path domain bridging step for generating two intermediate domains using the coarse-wise and the fine-wise data mixing techniques, alongside a cross-path knowledge distillation step for taking two complementary models trained on generated intermediate samples as 'teachers' to develop a superior 'student' in a multi-teacher distillation manner. These two optimization steps work in an alternating way and reinforce each other to give rise to DDB with strong adaptation power. Extensive experiments on adaptive segmentation tasks with different settings demonstrate that our DDB significantly outperforms state-of-the-art methods. Code is available at https://github.com/xiaoachen98/DDB.git.

cs.CV↗

arXiv2022

Sterile Neutrino Portal Dark Matter in $ν$THDM

In this paper, we propose the sterile neutrino portal dark matter in $ν$THDM. This model can naturally generate tiny neutrino mass with the neutrinophilic scalar doublet $Φ_ν$ and sterile neutrinos $N$ around TeV scale. Charged under a $Z_2$ symmetry, one Dirac fermion singlet $χ$ and one scalar singlet $ϕ$ are further introduced in the dark sector. The sterile neutrinos $N$ are the mediators between the DM and SM. Depending on the coupling strength, the DM can be either WIMP or FIMP. For the WIMP scenario, pair annihilation of DM into $NN$ is the key channel to satisfy various bounds, which could be tested at indirect detection experiments. For the FIMP scenario, besides the direct production of DM from freeze-in mechanism, contributions from late decay of NLSP is also important. When sterile neutrinos are heavier than the dark sector, NLSP is long-lived due to tiny mixing angle between sterile and light neutrinos. Constrains from free-streaming length, CMB, BBN and neutrino experiments are considered.

hep-ph↗

arXiv2022

Time-Frequency Analysis based Deep Interference Classification for Frequency Hopping System

It is known that, interference classification plays an important role in protecting the authorized communication system and avoiding its performance degradation in the hostile environment. In this paper, the interference classification problem for the frequency hopping communication system is discussed. Considering the possibility of presence multiple interferences in the frequency hopping system, in order to fully extract effective features of the interferences from the received signals, the linear and bilinear transform based composite time-frequency analysis method is adopted. Then the time-frequency spectrograms obtained from the time-frequency analysis are constructed as matching pairs and input to the deep neural network for classification. In particular, the Siamese neural network is used as the classifier, where the paired spectrograms are input into the two sub-networks of the deep networks, and these two sub-networks extract the features of the paired spectrograms for interference type classification. The simulation results confirm that the proposed algorithm can obtain higher classification accuracy than both traditional single time-frequency representation based approach and the AlexNet transfer learning or convolutional neural network based methods.

cs.NI↗

arXiv2022

Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptation

Adversarial learning has achieved remarkable performances for unsupervised domain adaptation (UDA). Existing adversarial UDA methods typically adopt an additional discriminator to play the min-max game with a feature extractor. However, most of these methods failed to effectively leverage the predicted discriminative information, and thus cause mode collapse for generator. In this work, we address this problem from a different perspective and design a simple yet effective adversarial paradigm in the form of a discriminator-free adversarial learning network (DALN), wherein the category classifier is reused as a discriminator, which achieves explicit domain alignment and category distinguishment through a unified objective, enabling the DALN to leverage the predicted discriminative information for sufficient feature alignment. Basically, we introduce a Nuclear-norm Wasserstein discrepancy (NWD) that has definite guidance meaning for performing discrimination. Such NWD can be coupled with the classifier to serve as a discriminator satisfying the K-Lipschitz constraint without the requirements of additional weight clipping or gradient penalty strategy. Without bells and whistles, DALN compares favorably against the existing state-of-the-art (SOTA) methods on a variety of public datasets. Moreover, as a plug-and-play technique, NWD can be directly used as a generic regularizer to benefit existing UDA algorithms. Code is available at https://github.com/xiaoachen98/DALN.

cs.CV↗

arXiv2022

Prototype Guided Network for Anomaly Segmentation

Semantic segmentation methods can not directly identify abnormal objects in images. Anomaly Segmentation algorithm from this realistic setting can distinguish between in-distribution objects and Out-Of-Distribution (OOD) objects and output the anomaly probability for pixels. In this paper, a Prototype Guided Anomaly segmentation Network (PGAN) is proposed to extract semantic prototypes for in-distribution training data from limited annotated images. In the model, prototypes are used to model the hierarchical category semantic information and distinguish OOD pixels. The proposed PGAN model includes a semantic segmentation network and a prototype extraction network. Similarity measures are adopted to optimize the prototypes. The learned semantic prototypes are used as category semantics to compare the similarity with features extracted from test images and then to generate semantic segmentation prediction. The proposed prototype extraction network can also be integrated into most semantic segmentation networks and recognize OOD pixels. On the StreetHazards dataset, the proposed PGAN model produced mIoU of 53.4% for anomaly segmentation. The experimental results demonstrate PGAN may achieve the SOTA performance in the anomaly segmentation tasks.

cs.CV↗

arXiv2022

Boundary Corrected Multi-scale Fusion Network for Real-time Semantic Segmentation

Image semantic segmentation aims at the pixel-level classification of images, which has requirements for both accuracy and speed in practical application. Existing semantic segmentation methods mainly rely on the high-resolution input to achieve high accuracy and do not meet the requirements of inference time. Although some methods focus on high-speed scene parsing with lightweight architectures, they can not fully mine semantic features under low computation with relatively low performance. To realize the real-time and high-precision segmentation, we propose a new method named Boundary Corrected Multi-scale Fusion Network, which uses the designed Low-resolution Multi-scale Fusion Module to extract semantic information. Moreover, to deal with boundary errors caused by low-resolution feature map fusion, we further design an additional Boundary Corrected Loss to constrain overly smooth features. Extensive experiments show that our method achieves a state-of-the-art balance of accuracy and speed for the real-time semantic segmentation.

cs.CV↗

arXiv2022

Near-field radiative heat transfer between hybrid polaritonic structures

Near-field radiative heat transfer between close objects may exceed the far-field blackbody radiation in orders of magnitude when exploiting polaritonic materials. Great efforts have been made to experimentally measure this fundamental stochastic effect but mostly based on simple materials. In this work, we foster an all-optical method to characterize the heat transfer between less explored plasmon-phonon hybrid polaritonic systems made of graphene-SiC heterostructures. A large heat flux about 26 times of the blackbody radiation limit is obtained over a 150-nm vacuum gap, attributed to the couplings of three different surface modes (plasmon, phonon polaritons and frustrated mode). The interaction of polaritonic modes in the hybrid system is also explored to build a switchable thermophotonic device with nearly unity heat flux tunability. This work paves the way for understanding mode-mediated near-field heat transfer and provides a platform for building thermophotonic or thermo-optoelectronic blocks for various applications.

physics.optics↗

arXiv2022

LighTN: Light-weight Transformer Network for Performance-overhead Tradeoff in Point Cloud Downsampling

Compared with traditional task-irrelevant downsampling methods, task-oriented neural networks have shown improved performance in point cloud downsampling range. Recently, Transformer family of networks has shown a more powerful learning capacity in visual tasks. However, Transformer-based architectures potentially consume too many resources which are usually worthless for low overhead task networks in downsampling range. This paper proposes a novel light-weight Transformer network (LighTN) for task-oriented point cloud downsampling, as an end-to-end and plug-and-play solution. In LighTN, a single-head self-correlation module is presented to extract refined global contextual features, where three projection matrices are simultaneously eliminated to save resource overhead, and the output of symmetric matrix satisfies the permutation invariant. Then, we design a novel downsampling loss function to guide LighTN focuses on critical point cloud regions with more uniform distribution and prominent points coverage. Furthermore, We introduce a feed-forward network scaling mechanism to enhance the learnable capacity of LighTN according to the expand-reduce strategy. The result of extensive experiments on classification and registration tasks demonstrates LighTN can achieve state-of-the-art performance with limited resource overhead.

cs.CV↗

arXiv2022

2D+3D facial expression recognition via embedded tensor manifold regularization

In this paper, a novel approach via embedded tensor manifold regularization for 2D+3D facial expression recognition (FERETMR) is proposed. Firstly, 3D tensors are constructed from 2D face images and 3D face shape models to keep the structural information and correlations. To maintain the local structure (geometric information) of 3D tensor samples in the low-dimensional tensors space during the dimensionality reduction, the $\ell_0$-norm of the core tensors and a tensor manifold regularization scheme embedded on core tensors are adopted via a low-rank truncated Tucker decomposition on the generated tensors. As a result, the obtained factor matrices will be used for facial expression classification prediction. To make the resulting tensor optimization more tractable, $\ell_1$-norm surrogate is employed to relax $\ell_0$-norm and hence the resulting tensor optimization problem has a nonsmooth objective function due to the $\ell_1$-norm and orthogonal constraints from the orthogonal Tucker decomposition. To efficiently tackle this tensor optimization problem, we establish the first-order optimality condition in terms of stationary points, and then design a block coordinate descent (BCD) algorithm with convergence analysis and the computational complexity. Numerical results on BU-3DFE database and Bosphorus databases demonstrate the effectiveness of our proposed approach.

cs.CV↗

arXiv2022

GLAN: A Graph-based Linear Assignment Network

Differentiable solvers for the linear assignment problem (LAP) have attracted much research attention in recent years, which are usually embedded into learning frameworks as components. However, previous algorithms, with or without learning strategies, usually suffer from the degradation of the optimality with the increment of the problem size. In this paper, we propose a learnable linear assignment solver based on deep graph networks. Specifically, we first transform the cost matrix to a bipartite graph and convert the assignment task to the problem of selecting reliable edges from the constructed graph. Subsequently, a deep graph network is developed to aggregate and update the features of nodes and edges. Finally, the network predicts a label for each edge that indicates the assignment relationship. The experimental results on a synthetic dataset reveal that our method outperforms state-of-the-art baselines and achieves consistently high accuracy with the increment of the problem size. Furthermore, we also embed the proposed solver, in comparison with state-of-the-art baseline solvers, into a popular multi-object tracking (MOT) framework to train the tracker in an end-to-end manner. The experimental results on MOT benchmarks illustrate that the proposed LAP solver improves the tracker by the largest margin.

cs.LG↗

arXiv2021

Investigating the $Z^\prime$ gauge boson at the future lepton colliders

$Z^\prime$ boson as a new gauge boson has been proposed in many new physics models. The interactions of $Z^\prime$ coupling to fermions are detailed studied at the large hadron collider. A $Z^\prime$ with the mass of a few TeV has been excluded in some special models. The future lepton colliders will focus on the studies of Higgs physics which provide the advantage to investigate the interactions of Higgs boson with the new gauge bosons. We investigate the $Z^\prime ZH$ interaction via the process of $e^+e^- \to Z^\prime/Z \to ZH \to l^+l^- b \bar{b}$. The angular distribution of the final leptons decaying from the $Z$-boson is related to the mixing of $Z^\prime$-$Z$ and the mass of $Z^\prime$. The forward-backward asymmetry has been proposed as an observable to investigate the $Z^\prime$-$Z$ mixing. The angular distributions change significantly with some special beam polarization comparing to the unpolarized condition.

hep-ph↗

arXiv2021

Camera-aware Style Separation and Contrastive Learning for Unsupervised Person Re-identification

Unsupervised person re-identification (ReID) is a challenging task without data annotation to guide discriminative learning. Existing methods attempt to solve this problem by clustering extracted embeddings to generate pseudo labels. However, most methods ignore the intra-class gap caused by camera style variance, and some methods are relatively complex and indirect although they try to solve the negative impact of the camera style on feature distribution. To solve this problem, we propose a camera-aware style separation and contrastive learning method (CA-UReID), which directly separates camera styles in the feature space with the designed camera-aware attention module. It can explicitly divide the learnable feature into camera-specific and camera-agnostic parts, reducing the influence of different cameras. Moreover, to further narrow the gap across cameras, we design a camera-aware contrastive center loss to learn more discriminative embedding for each identity. Extensive experiments demonstrate the superiority of our method over the state-of-the-art methods on the unsupervised person ReID task.

cs.CV↗

arXiv2021

Joint Graph Learning and Matching for Semantic Feature Correspondence

In recent years, powered by the learned discriminative representation via graph neural network (GNN) models, deep graph matching methods have made great progresses in the task of matching semantic features. However, these methods usually rely on heuristically generated graph patterns, which may introduce unreliable relationships to hurt the matching performance. In this paper, we propose a joint \emph{graph learning and matching} network, named GLAM, to explore reliable graph structures for boosting graph matching. GLAM adopts a pure attention-based framework for both graph learning and graph matching. Specifically, it employs two types of attention mechanisms, self-attention and cross-attention for the task. The self-attention discovers the relationships between features and to further update feature representations over the learnt structures; and the cross-attention computes cross-graph correlations between the two feature sets to be matched for feature reconstruction. Moreover, the final matching solution is directly derived from the output of the cross-attention layer, without employing a specific matching decision module. The proposed method is evaluated on three popular visual matching benchmarks (Pascal VOC, Willow Object and SPair-71k), and it outperforms previous state-of-the-art graph matching methods by significant margins on all benchmarks. Furthermore, the graph patterns learnt by our model are validated to be able to remarkably enhance previous deep graph matching methods by replacing their handcrafted graph structures with the learnt ones.

cs.CV↗

arXiv2021

MSO: Multi-Feature Space Joint Optimization Network for RGB-Infrared Person Re-Identification

The RGB-infrared cross-modality person re-identification (ReID) task aims to recognize the images of the same identity between the visible modality and the infrared modality. Existing methods mainly use a two-stream architecture to eliminate the discrepancy between the two modalities in the final common feature space, which ignore the single space of each modality in the shallow layers. To solve it, in this paper, we present a novel multi-feature space joint optimization (MSO) network, which can learn modality-sharable features in both the single-modality space and the common space. Firstly, based on the observation that edge information is modality-invariant, we propose an edge features enhancement module to enhance the modality-sharable features in each single-modality space. Specifically, we design a perceptual edge features (PEF) loss after the edge fusion strategy analysis. According to our knowledge, this is the first work that proposes explicit optimization in the single-modality feature space on cross-modality ReID task. Moreover, to increase the difference between cross-modality distance and class distance, we introduce a novel cross-modality contrastive-center (CMCC) loss into the modality-joint constraints in the common feature space. The PEF loss and CMCC loss jointly optimize the model in an end-to-end manner, which markedly improves the network's performance. Extensive experiments demonstrate that the proposed model significantly outperforms state-of-the-art methods on both the SYSU-MM01 and RegDB datasets.

cs.CV↗

arXiv2021

CMTR: Cross-modality Transformer for Visible-infrared Person Re-identification

Visible-infrared cross-modality person re-identification is a challenging ReID task, which aims to retrieve and match the same identity's images between the heterogeneous visible and infrared modalities. Thus, the core of this task is to bridge the huge gap between these two modalities. The existing convolutional neural network-based methods mainly face the problem of insufficient perception of modalities' information, and can not learn good discriminative modality-invariant embeddings for identities, which limits their performance. To solve these problems, we propose a cross-modality transformer-based method (CMTR) for the visible-infrared person re-identification task, which can explicitly mine the information of each modality and generate better discriminative features based on it. Specifically, to capture modalities' characteristics, we design the novel modality embeddings, which are fused with token embeddings to encode modalities' information. Furthermore, to enhance representation of modality embeddings and adjust matching embeddings' distribution, we propose a modality-aware enhancement loss based on the learned modalities' information, reducing intra-class distance and enlarging inter-class distance. To our knowledge, this is the first work of applying transformer network to the cross-modality re-identification task. We implement extensive experiments on the public SYSU-MM01 and RegDB datasets, and our proposed CMTR model's performance significantly surpasses existing outstanding CNN-based methods.

cs.CV↗