arXiv subjects

Feng Xue

Publications and source records attributed to Feng Xue.

At least 55 records · Page 3Linked to original sources

arXiv2024

Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks

Model quantization is widely used to compress and accelerate deep neural networks. However, recent studies have revealed the feasibility of weaponizing model quantization via implanting quantization-conditioned backdoors (QCBs). These special backdoors stay dormant on released full-precision models but will come into effect after standard quantization. Due to the peculiarity of QCBs, existing defenses have minor effects on reducing their threats or are even infeasible. In this paper, we conduct the first in-depth analysis of QCBs. We reveal that the activation of existing QCBs primarily stems from the nearest rounding operation and is closely related to the norms of neuron-wise truncation errors (i.e., the difference between the continuous full-precision weights and its quantized version). Motivated by these insights, we propose Error-guided Flipped Rounding with Activation Preservation (EFRAP), an effective and practical defense against QCBs. Specifically, EFRAP learns a non-nearest rounding strategy with neuron-wise error norm and layer-wise activation preservation guidance, flipping the rounding strategies of neurons crucial for backdoor effects but with minimal impact on clean accuracy. Extensive evaluations on benchmark datasets demonstrate that our EFRAP can defeat state-of-the-art QCB attacks under various settings. Code is available at https://github.com/AntigoneRandy/QuantBackdoor_EFRAP.

cs.CR↗

arXiv2024

An Efficient Learning-based Solver Comparable to Metaheuristics for the Capacitated Arc Routing Problem

Recently, neural networks (NN) have made great strides in combinatorial optimization. However, they face challenges when solving the capacitated arc routing problem (CARP) which is to find the minimum-cost tour covering all required edges on a graph, while within capacity constraints. In tackling CARP, NN-based approaches tend to lag behind advanced metaheuristics, since they lack directed arc modeling and efficient learning methods tailored for complex CARP. In this paper, we introduce an NN-based solver to significantly narrow the gap with advanced metaheuristics while exhibiting superior efficiency. First, we propose the direction-aware attention model (DaAM) to incorporate directionality into the embedding process, facilitating more effective one-stage decision-making. Second, we design a supervised reinforcement learning scheme that involves supervised pre-training to establish a robust initial policy for subsequent reinforcement fine-tuning. It proves particularly valuable for solving CARP that has a higher complexity than the node routing problems (NRPs). Finally, a path optimization method is proposed to adjust the depot return positions within the path generated by DaAM. Experiments illustrate that our approach surpasses heuristics and achieves decision quality comparable to state-of-the-art metaheuristics for the first time while maintaining superior efficiency.

cs.LG↗

arXiv2024

Switching intrinsic magnetic skyrmions with controllable magnetic anisotropy in van der Waals multiferroic heterostructures

Magnetic skyrmions, topologically nontrivial whirling spin textures at nanometer scales, have emerged as potential information carriers for spintronic devices. The ability to efficiently create and erase magnetic skyrmions is vital yet challenging for such applications. Based on first-principles studies, we find that switching between intrinsic magnetic skyrmion and high-temperature ferromagnetic states can be achieved in two-dimensional van der Waals (vdW) multiferroic heterostructure CrSeI/In2Te3 by reversing the ferroelectric polarization of In2Te3. The core mechanism of this switching is traced to the controllable magnetic anisotropy of CrSeI influenced by the ferroelectric polarization of In2Te3. We propose a useful descriptor linking the presence of magnetic skyrmions to magnetic parameters, and validate this connection through studies of a variety of similar vdW multiferroic heterostructures. Our work demonstrates that manipulating magnetic skyrmions via tunable magnetic anisotropies in vdW multiferroic heterostructures represents a highly promising and energy-efficient strategy for future development of spintronics.

cond-mat.mtrl-sci↗

arXiv2024

Valley-dependent Multiple Quantum States and Topological Transitions in Germanene-based Ferromagnetic van der Waals Heterostructures

Topological and valleytronic materials are promising for spintronic and quantum applications due to their unique properties. Using first principles calculations, we demonstrate that germanene (Ge)-based ferromagnetic heterostructures can exhibit multiple quantum states such as quantum anomalous Hall effect (QAHE) with Chern numbers of C=-1 or C=-2, quantum valley Hall effect (QVHE) with a valley Chern number of C$v$=2, valley-polarized quantum anomalous Hall effect (VP-QAHE) with two Chern numbers of C=-1 and C$v$=-1 as well as time-reversal symmetry broken quantum spin Hall effect (T-broken QSHE) with a spin Chern number of C$s$~1. Furthermore, we find that the transitions between different quantum states can occur by changing the magnetic orientation of ferromagnetic layers through applying a magnetic field. Our discovery provides new routes and novel material platforms with a unique combination of diverse properties that make it well suitable for applications in electronics, spintronics and valley electronics.

physics.comp-ph↗

arXiv2024

Exploiting Low-level Representations for Ultra-Fast Road Segmentation

Achieving real-time and accuracy on embedded platforms has always been the pursuit of road segmentation methods. To this end, they have proposed many lightweight networks. However, they ignore the fact that roads are "stuff" (background or environmental elements) rather than "things" (specific identifiable objects), which inspires us to explore the feasibility of representing roads with low-level instead of high-level features. Surprisingly, we find that the primary stage of mainstream network models is sufficient to represent most pixels of the road for segmentation. Motivated by this, we propose a Low-level Feature Dominated Road Segmentation network (LFD-RoadSeg). Specifically, LFD-RoadSeg employs a bilateral structure. The spatial detail branch is firstly designed to extract low-level feature representation for the road by the first stage of ResNet-18. To suppress texture-less regions mistaken as the road in the low-level feature, the context semantic branch is then designed to extract the context feature in a fast manner. To this end, in the second branch, we asymmetrically downsample the input image and design an aggregation module to achieve comparable receptive fields to the third stage of ResNet-18 but with less time consumption. Finally, to segment the road from the low-level feature, a selective fusion module is proposed to calculate pixel-wise attention between the low-level representation and context feature, and suppress the non-road low-level response by this attention. On KITTI-Road, LFD-RoadSeg achieves a maximum F1-measure (MaxF) of 95.21% and an average precision of 93.71%, while reaching 238 FPS on a single TITAN Xp and 54 FPS on a Jetson TX2, all with a compact model size of just 936k parameters. The source code is available at https://github.com/zhouhuan-hust/LFD-RoadSeg.

cs.CV↗

arXiv2024

MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Images

This paper studies zero-shot anomaly classification (AC) and segmentation (AS) in industrial vision. We reveal that the abundant normal and abnormal cues implicit in unlabeled test images can be exploited for anomaly determination, which is ignored by prior methods. Our key observation is that for the industrial product images, the normal image patches could find a relatively large number of similar patches in other unlabeled images, while the abnormal ones only have a few similar patches. We leverage such a discriminative characteristic to design a novel zero-shot AC/AS method by Mutual Scoring (MuSc) of the unlabeled images, which does not need any training or prompts. Specifically, we perform Local Neighborhood Aggregation with Multiple Degrees (LNAMD) to obtain the patch features that are capable of representing anomalies in varying sizes. Then we propose the Mutual Scoring Mechanism (MSM) to leverage the unlabeled test images to assign the anomaly score to each other. Furthermore, we present an optimization approach named Re-scoring with Constrained Image-level Neighborhood (RsCIN) for image-level anomaly classification to suppress the false positives caused by noises in normal images. The superior performance on the challenging MVTec AD and VisA datasets demonstrates the effectiveness of our approach. Compared with the state-of-the-art zero-shot approaches, MuSc achieves a $\textbf{21.1%}$ PRO absolute gain (from 72.7% to 93.8%) on MVTec AD, a $\textbf{19.4%}$ pixel-AP gain and a $\textbf{14.7%}$ pixel-AUROC gain on VisA. In addition, our zero-shot approach outperforms most of the few-shot approaches and is comparable to some one-class methods. Code is available at https://github.com/xrli-U/MuSc.

cs.CV↗

arXiv2024

Indoor Obstacle Discovery on Reflective Ground via Monocular Camera

Visual obstacle discovery is a key step towards autonomous navigation of indoor mobile robots. Successful solutions have many applications in multiple scenes. One of the exceptions is the reflective ground. In this case, the reflections on the floor resemble the true world, which confuses the obstacle discovery and leaves navigation unsuccessful. We argue that the key to this problem lies in obtaining discriminative features for reflections and obstacles. Note that obstacle and reflection can be separated by the ground plane in 3D space. With this observation, we firstly introduce a pre-calibration based ground detection scheme that uses robot motion to predict the ground plane. Due to the immunity of robot motion to reflection, this scheme avoids failed ground detection caused by reflection. Given the detected ground, we design a ground-pixel parallax to describe the location of a pixel relative to the ground. Based on this, a unified appearance-geometry feature representation is proposed to describe objects inside rectangular boxes. Eventually, based on segmenting by detection framework, an appearance-geometry fusion regressor is designed to utilize the proposed feature to discover the obstacles. It also prevents our model from concentrating too much on parts of obstacles instead of whole obstacles. For evaluation, we introduce a new dataset for Obstacle on Reflective Ground (ORG), which comprises 15 scenes with various ground reflections, a total of more than 200 image sequences and 3400 RGB images. The pixel-wise annotations of ground and obstacle provide a comparison to our method and other methods. By reducing the misdetection of the reflection, the proposed approach outperforms others. The source code and the dataset will be available at https://github.com/XuefengBUPT/IndoorObstacleDiscovery-RG.

cs.CV↗

arXiv2023

Intrinsic and tunable quantum anomalous Hall effect and magnetic topological phases in XYBi2Te5

By first-principles calculations, we study the magnetic and topological properties of XYBi2Te5-family (X, Y = Mn, Ni, V, Eu) compounds. The strongly coupled double magnetic atom-layers can significantly enhance the magnetic ordering temperature while keeping the topologically nontrivial properties. Particularly, NiVBi2Te5 is found to be a magnetic Weyl semimetal in bulk and a Chern insulator in thin film with both the Curie temperature (~150 K) and full gap well above 77 K. Ni2Bi2Te5, MnNiBi2Te5, NiVBi2Te5 and NiEuBi2Te5 exhibits intrinsic dynamic axion state. Among them, MnNiBi2Te5 has a Neel temperature over 200 K and Ni2Bi2Te5 even demonstrates antiferromagnetic order above room temperature. These results indicate an approach to realize high temperature quantum anomalous Hall effect and other topological quantum effects for practical applications.

cond-mat.mtrl-sci↗

arXiv2023

Unknown Sniffer for Object Detection: Don't Turn a Blind Eye to Unknown Objects

The recently proposed open-world object and open-set detection have achieved a breakthrough in finding never-seen-before objects and distinguishing them from known ones. However, their studies on knowledge transfer from known classes to unknown ones are not deep enough, resulting in the scanty capability for detecting unknowns hidden in the background. In this paper, we propose the unknown sniffer (UnSniffer) to find both unknown and known objects. Firstly, the generalized object confidence (GOC) score is introduced, which only uses known samples for supervision and avoids improper suppression of unknowns in the background. Significantly, such confidence score learned from known objects can be generalized to unknown ones. Additionally, we propose a negative energy suppression loss to further suppress the non-object samples in the background. Next, the best box of each unknown is hard to obtain during inference due to lacking their semantic information in training. To solve this issue, we introduce a graph-based determination scheme to replace hand-designed non-maximum suppression (NMS) post-processing. Finally, we present the Unknown Object Detection Benchmark, the first publicly benchmark that encompasses precision evaluation for unknown detection to our knowledge. Experiments show that our method is far better than the existing state-of-the-art methods.

cs.CV↗

arXiv2023

Balanced Line Coverage in Large-scale Urban Scene

Line coverage is to cover linear infrastructure modeled as 1D segments by robots, which received attention in recent years. With the increasing urbanization, the area of the city and the density of infrastructure continues to increase, which brings two issues: (1) Due to the energy constraint, it is hard for the homogeneous robot team to cover the large-scale linear infrastructure starting from one depot; (2) In the large urban scene, the imbalance of robots' path greatly extends the time cost of the multi-robot system, which is more serious than that in smaller-size scenes. To address these issues, we propose a heterogeneous multi-robot approach consisting of several teams, each of which contains one transportation robot (TRob) and several coverage robots (CRobs). Firstly, a balanced graph partitioning (BGP) algorithm is proposed to divide the road network into several similar-size sub-graphs, and then the TRob delivers a group of CRobs to the subgraph region quickly. Secondly, a balanced ulusoy partitioning (BUP) algorithm is proposed to extract similar-length tours for each CRob from the sub-graph. Abundant experiments are conducted on seven road networks ranging in scales that are collected in this paper. Our method achieves robot utilization of 90% and the best maximal tour length at the cost of a small increase in total tour length, which further minimizes the time cost of the whole system. The source code and the road networks are available at https://github.com/suhangsong/BLC-LargeScale.

cs.RO↗

arXiv2023

A generalized forward-backward splitting operator: Degenerate analysis and applications

In this paper, we study the nonexpansive properties of a generalized forward-backward splitting (G-FBS) operator, particularly under the setting of degenerate metric, from which follow the convergence results in terms of degenerate metric of the associated fixed-point iterations. The descent lemma and sufficient decrease property are also extended to degenerate case. It is further shown that the G-FBS operator provides a simplifying and unifying framework to model and analyze a great variety of operator splitting algorithms, many existing results are exactly recovered or relaxed from our general results.

math.OC↗

arXiv2023

The operator splitting schemes revisited: primal-dual gap and degeneracy reduction by a unified analysis

We revisit the operator splitting schemes proposed in a recent work of [Some extensions of the operator splitting schemes based on Lagrangian and primal-dual: A unified proximal point analysis, Feng Xue, Optimization, 2022, doi: 10.1080/02331934.2022.2057309], and further analyze the convergence of the generalized Bregman distance and the primal-dual gap of these algorithms within a unified proximal point framework. The possibility of reduction to a simple resolvent is also discussed by exploiting the structure and possible degeneracy of the underlying metric.

math.OC↗

arXiv2023

On Douglas-Rachford splitting that generally fails to be a proximal mapping: A degenerate proximal point analysis

Based on a degenerate proximal point analysis, we show that the Douglas-Rachford splitting can be reduced to a well-defined resolvent, but generally fails to be a proximal mapping. This extends the recent result of [Bauschke, Schaad and Wang. Math. Program., 168 (2018), pp. 55-61] to more general setting. The related concepts and consequences are also discussed. In particular, the results regarding the maximal and cyclic monotonicity are instrumental for analyzing many operator splitting algorithms.

math.OC↗

arXiv2023

LipFormer: Learning to Lipread Unseen Speakers based on Visual-Landmark Transformers

Lipreading refers to understanding and further translating the speech of a speaker in the video into natural language. State-of-the-art lipreading methods excel in interpreting overlap speakers, i.e., speakers appear in both training and inference sets. However, generalizing these methods to unseen speakers incurs catastrophic performance degradation due to the limited number of speakers in training bank and the evident visual variations caused by the shape/color of lips for different speakers. Therefore, merely depending on the visible changes of lips tends to cause model overfitting. To address this problem, we propose to use multi-modal features across visual and landmarks, which can describe the lip motion irrespective to the speaker identities. Then, we develop a sentence-level lipreading framework based on visual-landmark transformers, namely LipFormer. Specifically, LipFormer consists of a lip motion stream, a facial landmark stream, and a cross-modal fusion. The embeddings from the two streams are produced by self-attention, which are fed to the cross-attention module to achieve the alignment between visuals and landmarks. Finally, the resulting fused features can be decoded to output texts by a cascade seq2seq model. Experiments demonstrate that our method can effectively enhance the model generalization to unseen speakers.

cs.CV↗

arXiv2023

Boosting Out-of-Distribution Detection with Multiple Pre-trained Models

Out-of-Distribution (OOD) detection, i.e., identifying whether an input is sampled from a novel distribution other than the training distribution, is a critical task for safely deploying machine learning systems in the open world. Recently, post hoc detection utilizing pre-trained models has shown promising performance and can be scaled to large-scale problems. This advance raises a natural question: Can we leverage the diversity of multiple pre-trained models to improve the performance of post hoc detection methods? In this work, we propose a detection enhancement method by ensembling multiple detection decisions derived from a zoo of pre-trained models. Our approach uses the p-value instead of the commonly used hard threshold and leverages a fundamental framework of multiple hypothesis testing to control the true positive rate of In-Distribution (ID) data. We focus on the usage of model zoos and provide systematic empirical comparisons with current state-of-the-art methods on various OOD detection benchmarks. The proposed ensemble scheme shows consistent improvement compared to single-model detectors and significantly outperforms the current competitive methods. Our method substantially improves the relative performance by 65.40% and 26.96% on the CIFAR10 and ImageNet benchmarks.

cs.LG↗

arXiv2022

Tunable Quantum Anomalous Hall Effects in Ferromagnetic van der Waals Heterostructures

The quantum anomalous Hall effect (QAHE) has unique advantages in topotronic applications, but it is still challenging to realize the QAHE with tunable magnetic and topological properties for building functional devices. Through systematic first-principles calculations, we predict that the in-plane magnetization induced QAHE with Chern numbers C = $\pm$1 and the out-of-plane magnetization induced QAHE with high Chern numbers C = $\pm$3 can be realized in a single material candidate, which is composed of van der Waals (vdW) coupled Bi and MnBi$_2$Te$_4$ monolayers. The switching between different phases of QAHE can be controllable by multiple ways, such as applying strain or (weak) magnetic field or twisting the vdW materials. The prediction of an experimentally available material system hosting robust, highly tunable QAHE will stimulate great research interest in the field. Our work opens a new avenue for the realization of tunable QAHE and provides a practical material platform for the development of topological electronics.

physics.comp-ph↗

arXiv2022

MEGCF: Multimodal Entity Graph Collaborative Filtering for Personalized Recommendation

In most E-commerce platforms, whether the displayed items trigger the user's interest largely depends on their most eye-catching multimodal content. Consequently, increasing efforts focus on modeling multimodal user preference, and the pressing paradigm is to incorporate complete multimodal deep features of the items into the recommendation module. However, the existing studies ignore the mismatch problem between multimodal feature extraction (MFE) and user interest modeling (UIM). That is, MFE and UIM have different emphases. Specifically, MFE is migrated from and adapted to upstream tasks such as image classification. In addition, it is mainly a content-oriented and non-personalized process, while UIM, with its greater focus on understanding user interaction, is essentially a user-oriented and personalized process. Therefore, the direct incorporation of MFE into UIM for purely user-oriented tasks, tends to introduce a large number of preference-independent multimodal noise and contaminate the embedding representations in UIM. This paper aims at solving the mismatch problem between MFE and UIM, so as to generate high-quality embedding representations and better model multimodal user preferences. Towards this end, we develop a novel model, MEGCF. The UIM of the proposed model captures the semantic correlation between interactions and the features obtained from MFE, thus making a better match between MFE and UIM. More precisely, semantic-rich entities are first extracted from the multimodal data, since they are more relevant to user preferences than other multimodal information. These entities are then integrated into the user-item interaction graph. Afterwards, a symmetric linear Graph Convolution Network (GCN) module is constructed to perform message propagation over the graph, in order to capture both high-order semantic correlation and collaborative filtering signals.

cs.IR↗

arXiv2022

Joint Multi-grained Popularity-aware Graph Convolution Collaborative Filtering for Recommendation

Graph Convolution Networks (GCNs), with their efficient ability to capture high-order connectivity in graphs, have been widely applied in recommender systems. Stacking multiple neighbor aggregation is the major operation in GCNs. It implicitly captures popularity features because the number of neighbor nodes reflects the popularity of a node. However, existing GCN-based methods ignore a universal problem: users' sensitivity to item popularity is differentiated, but the neighbor aggregations in GCNs actually fix this sensitivity through Graph Laplacian Normalization, leading to suboptimal personalization. In this work, we propose to model multi-grained popularity features and jointly learn them together with high-order connectivity, to match the differentiation of user preferences exhibited in popularity features. Specifically, we develop a Joint Multi-grained Popularity-aware Graph Convolution Collaborative Filtering model, short for JMP-GCF, which uses a popularity-aware embedding generation to construct multi-grained popularity features, and uses the idea of joint learning to capture the signals within and between different granularities of popularity features that are relevant for modeling user preferences. Additionally, we propose a multistage stacked training strategy to speed up model convergence. We conduct extensive experiments on three public datasets to show the state-of-the-art performance of JMP-GCF.

cs.IR↗