Xiaofu Wu

Quan Zhou, Huimin Shi, Weikang Xiang et al.

The recent advances of compressing high-accuracy convolution neural networks (CNNs) have witnessed remarkable progress for real-time object detection. To accelerate detection speed, lightweight detectors always have few convolution layers using single-path backbone. Single-path architecture, however, involves continuous pooling and downsampling operations, always resulting in coarse and inaccurate feature maps that are disadvantageous to locate objects. On the other hand, due to limited network capacity, recent lightweight networks are often weak in representing large scale visual data. To address these problems, this paper presents a dual-path network, named DPNet, with a lightweight attention scheme for real-time object detection. The dual-path architecture enables us to parallelly extract high-level semantic features and low-level object details. Although DPNet has nearly duplicated shape with respect to single-path detectors, the computational costs and model size are not significantly increased. To enhance representation capability, a lightweight self-correlation module (LSCM) is designed to capture global interactions, with only few computational overheads and network parameters. In neck, LSCM is extended into a lightweight crosscorrelation module (LCCM), capturing mutual dependencies among neighboring scale features. We have conducted exhaustive experiments on MS COCO and Pascal VOC 2007 datasets. The experimental results demonstrate that DPNet achieves state-of the-art trade-off between detection accuracy and implementation efficiency. Specifically, DPNet achieves 30.5% AP on MS COCO test-dev and 81.5% mAP on Pascal VOC 2007 test set, together mwith nearly 2.5M model size, 1.04 GFLOPs, and 164 FPS and 196 FPS for 320 x 320 input images of two datasets.

Suofei Zhang, Xinxin Wang, Xiaofu Wu et al.

Existing deep learning-based cross-view geo-localization methods primarily focus on improving the accuracy of cross-domain image matching, rather than enabling models to comprehensively capture contextual information around the target and minimize the cost of localization errors. To support systematic research into this Distance-Aware Cross-View Geo-Localization (DACVGL) problem, we construct Distance-Aware Campus (DA-Campus), the first benchmark that pairs multi-view imagery with precise distance annotations across three spatial resolutions. Based on DA-Campus, we formulate DACVGL as a hierarchical retrieval problem across different domains. Our study further reveals that, due to the inherent complexity of spatial relationships among buildings, this problem can only be addressed via a contrastive learning paradigm, rather than conventional metric learning. To tackle this challenge, we propose Dynamic Contrastive Learning (DyCL), a novel framework that progressively aligns feature representations according to hierarchical spatial margins. Extensive experiments demonstrate that DyCL is highly complementary to existing multi-scale metric learning methods and yields substantial improvements in both hierarchical retrieval performance and overall cross-view geo-localization accuracy. Our code and benchmark are publicly available at https://github.com/anocodetest1/DyCL.

Jianshu Zhang, Xiaofu Wu, Junquan Hu

This paper investigates the anti-jamming channel access problem in complex and unknown jamming environments, where the jammer could dynamically adjust its strategies to target different channels. Traditional channel hopping anti-jamming approaches using fixed patterns are ineffective against such dynamic jamming attacks. Although the emerging deep reinforcement learning (DRL) based dynamic channel access approach could achieve the Nash equilibrium under fast-changing jamming attacks, it requires extensive training episodes. To address this issue, we propose a fast adaptive anti-jamming channel access approach guided by the intuition of ``learning faster than the jammer", where a synchronously updated coarse-grained spectrum prediction serves as an auxiliary task for the deep Q learning (DQN) based anti-jamming model. This helps the model identify a superior Q-function compared to standard DRL while significantly reducing the number of training episodes. Numerical results indicate that the proposed approach significantly accelerates the rate of convergence in model training, reducing the required training episodes by up to 70% compared to standard DRL. Additionally, it also achieves a 10% improvement in throughput over NE strategies, owing to the effective use of coarse-grained spectrum prediction.

Linjie Wang, Quan Zhou, Chenfeng Jiang et al.

Due to the powerful ability to encode image details and semantics, many lightweight dual-resolution networks have been proposed in recent years. However, most of them ignore the benefit of boundary information. This paper introduces a lightweight dual-resolution network, called DRBANet, aiming to refine semantic segmentation results with the aid of boundary information. DRBANet adopts dual parallel architecture, including: high resolution branch (HRB) and low resolution branch (LRB). Specifically, HRB mainly consists of a set of Efficient Inverted Bottleneck Modules (EIBMs), which learn feature representations with larger receptive fields. LRB is composed of a series of EIBMs and an Extremely Lightweight Pyramid Pooling Module (ELPPM), where ELPPM is utilized to capture multi-scale context through hierarchical residual connections. Finally, a boundary supervision head is designed to capture object boundaries in HRB. Extensive experiments on Cityscapes and CamVid datasets demonstrate that our method achieves promising trade-off between segmentation accuracy and running efficiency.

Huimin Shi, Quan Zhou, Yinghao Ni et al.

Object detection often costs a considerable amount of computation to get satisfied performance, which is unfriendly to be deployed in edge devices. To address the trade-off between computational cost and detection accuracy, this paper presents a dual path network, named DPNet, for efficient object detection with lightweight self-attention. In backbone, a single input/output lightweight self-attention module (LSAM) is designed to encode global interactions between different positions. LSAM is also extended into a multiple-inputs version in feature pyramid network (FPN), which is employed to capture cross-resolution dependencies in two paths. Extensive experiments on the COCO dataset demonstrate that our method achieves state-of-the-art detection results. More specifically, DPNet obtains 29.0% AP on COCO test-dev, with only 1.14 GFLOPs and 2.27M model size for a 320x320 image.

Yueming Yin, Zhen Yang, Haifeng Hu et al.

Unsupervised domain adaptation enables intelligent models to transfer knowledge from a labeled source domain to a similar but unlabeled target domain. Recent study reveals that knowledge can be transferred from one source domain to another unknown target domain, called Universal Domain Adaptation (UDA). However, in the real-world application, there are often more than one source domain to be exploited for domain adaptation. In this paper, we formally propose a more general domain adaptation setting, universal multi-source domain adaptation (UMDA), where the label sets of multiple source domains can be different and the label set of target domain is completely unknown. The main challenges in UMDA are to identify the common label set between each source domain and target domain, and to keep the model scalable as the number of source domains increases. To address these challenges, we propose a universal multi-source adaptation network (UMAN) to solve the domain adaptation problem without increasing the complexity of the model in various UMDA settings. In UMAN, we estimate the reliability of each known class in the common label set via the prediction margin, which helps adversarial training to better align the distributions of multiple source domains and target domain in the common label set. Moreover, the theoretical guarantee for UMAN is also provided. Massive experimental results show that existing UDA and multi-source DA (MDA) methods cannot be directly applied to UMDA and the proposed UMAN achieves the state-of-the-art performance in various UMDA settings.

Yueming Yin, Zhen Yang, Xiaofu Wu et al.

As a more practical setting for unsupervised domain adaptation, Universal Domain Adaptation (UDA) is recently introduced, where the target label set is unknown. One of the big challenges in UDA is how to determine the common label set shared by source and target domains, as there is simply no labeling available in the target domain. In this paper, we employ a probabilistic approach for locating the common label set, where each source class may come from the common label set with a probability. In particular, we propose a novel approach for evaluating the probability of each source class from the common label set, where this probability is computed by the prediction margin accumulated over the whole target domain. Then, we propose a simple universal adaptation network (S-UAN) by incorporating the probabilistic structure for the common label set. Finally, we analyse the generalization bound focusing on the common label set and explore the properties on the target risk for UDA. Extensive experiments indicate that S-UAN works well in different UDA settings and outperforms the state-of-the-art methods by large margins.

Lei Zhang, Xiaofu Wu, Suofei Zhang et al.

Multi-branch is extensively studied for learning rich feature representation for person re-identification (Re-ID). In this paper, we propose a branch-cooperative architecture over OSNet, termed BC-OSNet, for person Re-ID. By stacking four cooperative branches, namely, a global branch, a local branch, a relational branch and a contrastive branch, we obtain powerful feature representation for person Re-ID. Extensive experiments show that the proposed BC-OSNet achieves state-of-art performance on the three popular datasets, including Market-1501, DukeMTMC-reID and CUHK03. In particular, it achieves mAP of 84.0% and rank-1 accuracy of 87.1% on the CUHK03_labeled.

Yueming Yin, Zhen Yang, Haifeng Hu et al.

Domain alignment (DA) has been widely used in unsupervised domain adaptation. Many existing DA methods assume that a low source risk, together with the alignment of distributions of source and target, means a low target risk. In this paper, we show that this does not always hold. We thus propose a novel metric-learning-assisted domain adaptation (MLA-DA) method, which employs a novel triplet loss for helping better feature alignment. We explore the relationship between the second largest probability of a target sample's prediction and its distance to the decision boundary. Based on the relationship, we propose a novel mechanism to adaptively adjust the margin in the triplet loss according to target predictions. Experimental results show that the use of proposed triplet loss can achieve clearly better results. We also demonstrate the performance improvement of MLA-DA on all four standard benchmarks compared with the state-of-the-art unsupervised domain adaptation methods. Furthermore, MLA-DA shows stable performance in robust experiments.

Quan Zhou, Dechun Cong, Bin Kang et al.

Exploring contextual information in convolution neural networks (CNNs) has gained substantial attention in recent years for semantic segmentation. This paper introduces a Bi-directional Contextual Aggregating Network, called BiCANet, for semantic segmentation. Unlike previous approaches that encode context in feature space, BiCANet aggregates contextual cues from a categorical perspective, which is mainly consist of three parts: contextual condensed projection block (CCPB), bi-directional context interaction block (BCIB), and muti-scale contextual fusion block (MCFB). More specifically, CCPB learns a category-based mapping through a split-transform-merge architecture, which condenses contextual cues with different receptive fields from intermediate layer. BCIB, on the other hand, employs dense skipped-connections to enhance the class-level context exchanging. Finally, MCFB integrates multi-scale contextual cues by investigating short- and long-ranged spatial dependencies. To evaluate BiCANet, we have conducted extensive experiments on three semantic segmentation datasets: PASCAL VOC 2012, Cityscapes, and ADE20K. The experimental results demonstrate that BiCANet outperforms recent state-of-the-art networks without any postprocess techniques. Particularly, BiCANet achieves the mIoU score of 86.7%, 82.4% and 38.66% on PASCAL VOC 2012, Cityscapes and ADE20K testset, respectively.

Xiaofu Wu, Ben Xie, Shiliang Zhao et al.

A big challenge of person re-identification (Re-ID) using a multi-branch network architecture is to learn diverse features from the ID-labeled dataset. The 2-branch Batch DropBlock (BDB) network was recently proposed for achieving diversity between the global branch and the feature-dropping branch. In this paper, we propose to move the dropping operation from the intermediate feature layer towards the input (image dropping). Since it may drop a large portion of input images, this makes the training hard to converge. Hence, we propose a novel double-batch-split co-training approach for remedying this problem. In particular, we show that the feature diversity can be well achieved with the use of multiple dropping branches by setting individual dropping ratio for each branch. Empirical evidence demonstrates that the proposed method performs superior to BDB on popular person Re-ID datasets, including Market-1501, DukeMTMC-reID and CUHK03 and the use of more dropping branches can further boost the performance.

Xiaofu Wu, Suofei hang, Quan Zhou et al.

Entropy minimization has been widely used in unsupervised domain adaptation (UDA). However, existing works reveal that entropy minimization only may result into collapsed trivial solutions. In this paper, we propose to avoid trivial solutions by further introducing diversity maximization. In order to achieve the possible minimum target risk for UDA, we show that diversity maximization should be elaborately balanced with entropy minimization, the degree of which can be finely controlled with the use of deep embedded validation in an unsupervised manner. The proposed minimal-entropy diversity maximization (MEDM) can be directly implemented by stochastic gradient descent without use of adversarial learning. Empirical evidence demonstrates that MEDM outperforms the state-of-the-art methods on four popular domain adaptation datasets.

Ben Xie, Xiaofu Wu, Suofei Zhang et al.

Learning diverse features is key to the success of person re-identification. Various part-based methods have been extensively proposed for learning local representations, which, however, are still inferior to the best-performing methods for person re-identification. This paper proposes to construct a strong lightweight network architecture, termed PLR-OSNet, based on the idea of Part-Level feature Resolution over the Omni-Scale Network (OSNet) for achieving feature diversity. The proposed PLR-OSNet has two branches, one branch for global feature representation and the other branch for local feature representation. The local branch employs a uniform partition strategy for part-level feature resolution but produces only a single identity-prediction loss, which is in sharp contrast to the existing part-based methods. Empirical evidence demonstrates that the proposed PLR-OSNet achieves state-of-the-art performance on popular person Re-ID datasets, including Market1501, DukeMTMC-reID and CUHK03, despite its small model size.

Jia Liu, Quan Zhou, Yong Qiang et al.

This paper introduces a lightweight convolutional neural network, called FDDWNet, for real-time accurate semantic segmentation. In contrast to recent advances of lightweight networks that prefer to utilize shallow structure, FDDWNet makes an effort to design more deeper network architecture, while maintains faster inference speed and higher segmentation accuracy. Our network uses factorized dilated depth-wise separable convolutions (FDDWC) to learn feature representations from different scale receptive fields with fewer model parameters. Additionally, FDDWNet has multiple branches of skipped connections to gather context cues from intermediate convolution layers. The experiments show that FDDWNet only has 0.8M model size, while achieves 60 FPS running speed on a single RTX 2080Ti GPU with a 1024x512 input image. The comprehensive experiments demonstrate that our model achieves state-of-the-art results in terms of available speed and accuracy trade-off on CityScapes and CamVid datasets.

Yu Wang, Quan Zhou, Xiaofu Wu

The recent years have witnessed great advances for semantic segmentation using deep convolutional neural networks (DCNNs). However, a large number of convolutional layers and feature channels lead to semantic segmentation as a computationally heavy task, which is disadvantage to the scenario with limited resources. In this paper, we design an efficient symmetric network, called (ESNet), to address this problem. The whole network has nearly symmetric architecture, which is mainly composed of a series of factorized convolution unit (FCU) and its parallel counterparts (PFCU). On one hand, the FCU adopts a widely-used 1D factorized convolution in residual layers. On the other hand, the parallel version employs a transform-split-transform-merge strategy in the designment of residual module, where the split branch adopts dilated convolutions with different rate to enlarge receptive field. Our model has nearly 1.6M parameters, and is able to be performed over 62 FPS on a single GTX 1080Ti GPU. The experiments demonstrate that our approach achieves state-of-the-art results in terms of speed and accuracy trade-off for real-time semantic segmentation on CityScapes dataset.

Yu Wang, Quan Zhou, Jia Liu et al.

The extensive computational burden limits the usage of CNNs in mobile devices for dense estimation tasks. In this paper, we present a lightweight network to address this problem,namely LEDNet, which employs an asymmetric encoder-decoder architecture for the task of real-time semantic segmentation.More specifically, the encoder adopts a ResNet as backbone network, where two new operations, channel split and shuffle, are utilized in each residual block to greatly reduce computation cost while maintaining higher segmentation accuracy. On the other hand, an attention pyramid network (APN) is employed in the decoder to further lighten the entire network complexity. Our model has less than 1M parameters,and is able to run at over 71 FPS in a single GTX 1080Ti GPU. The comprehensive experiments demonstrate that our approach achieves state-of-the-art results in terms of speed and accuracy trade-off on CityScapes dataset.

Suofei Zhang, Wei Zhao, Xiaofu Wu et al.

Capsules as well as dynamic routing between them are most recently proposed structures for deep neural networks. A capsule groups data into vectors or matrices as poses rather than conventional scalars to represent specific properties of target instance. Besides of pose, a capsule should be attached with a probability (often denoted as activation) for its presence. The dynamic routing helps capsules achieve more generalization capacity with many fewer model parameters. However, the bottleneck that prevents widespread applications of capsule is the expense of computation during routing. To address this problem, we generalize existing routing methods within the framework of weighted kernel density estimation, and propose two fast routing methods with different optimization strategies. Our methods prompt the time efficiency of routing by nearly 40\% with negligible performance degradation. By stacking a hybrid of convolutional layers and capsule layers, we construct a network architecture to handle inputs at a resolution of $64\times{64}$ pixels. The proposed models achieve a parallel performance with other leading methods in multiple benchmarks.

Xiaofu Wu, Zhen Yang, Cong Ling et al.

In the past, two main approaches for the purpose of authentication, including information-theoretic authentication codes and complexity-theoretic message authentication codes (MACs), were almost independently developed. In this paper, we propose a new cryptographic primitive, namely, artificial-noise-aided MACs (ANA-MACs), which can be considered as both computationally secure and information-theoretically secure. For ANA-MACs, we introduce artificial noise to interfere with the complexity-theoretic MACs and quantization is further employed to facilitate packet-based transmission. With a channel coding formulation of key recovery in the MACs, the generation of standard authentication tags can be seen as an encoding process for the ensemble of codes, where the shared key between Alice and Bob is considered as the input and the message is used to specify a code from the ensemble of codes. Then, we show that the introduction of artificial noise in ANA-MACs can be well employed to resist the key recovery attack even if the opponent has an unlimited computing power. Finally, a pragmatic approach for the analysis of ANA-MACs is provided, and we show how to balance the three performance metrics, including the completeness error, the false acceptance probability, and the conditional equivocation about the key. The analysis can be well applied to a class of ANA-MACs, where MACs with Rijndael cipher are employed.