Rui Zhang

Rui Zhang

Auto-generated profile, based on publicly available information

Rui Zhang

Army Engineering University of PLA, Nanjing, China

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 February 2025 in Engineering Applications of Artificial Intelligence
Verified
Journal Article
Closed access
PWPeichao Wang
Peichao Wang
JWJiabao Wang
Jiabao Wang
YCYao Chen
Yao Chen
RZRui Zhang
Rui Zhang
YLYang Li
Yang Li
ZMZhuang Miao
Zhuang Miao

8 September 2020 in IEEE Access
Verified
Journal Article
Open access
YLYang Li
Yang Li
YWYapeng Wang
Yapeng Wang
ZMZhuang Miao
Zhuang Miao
JWJiabao Wang
Jiabao Wang
RZRui Zhang
Rui Zhang
Recently, unsupervised deep hashing has attracted increasing attention, mainly because of its potential ability to learn binary codes without identity annotations. However, because the labels are predicted by their pretext tasks, unsupervised deep hashing becomes unstable when learning with noisy labels. To mitigate this issue, we propose a simple but effective approach to self-supervised hash learning based on dual pseudo agreement. By adding a consistency constraint, our method can prevent corrupted labels and encourage generalization for effective knowledge distillation. Specifically, we use the refined pseudo labels as a stabilization constraint to train hash codes, which can implicitly encode semantic structures of the data into the learned Hamming space. Based on the stable pseudo labels, we propose a self-supervised hashing method with mutual information and noise contrastive loss. Throughout the process of hash learning, the stable pseudo labels and data distributions collaboratively work together as teachers to guide the binary codes learning process. Extensive experiments on three publicly available datasets demonstrate that the proposed method can consistently outperform state-of-the-art methods by large margins.

18 November 2019 in IEEE Access
Verified
Journal Article
Open access
JWJiabao Wang
Jiabao Wang
YLYang Li
Yang Li
ZMZhuang Miao
Zhuang Miao
XZXun Zhao
Xun Zhao
ZRZhang Rui
Zhang Rui
The application of fine-grained image classification can be problematic due to subtle differences between classes. The existing global feature-based methods have worse accuracies than regional feature-based methods, because regional feature-based methods focus on the determination of differentiated features within local regions. To learn more discriminative global features, in this paper, we proposed the use of L2 normalization to tackle a neglected conflict between the widely used metric loss (triplet loss) and classification loss (softmax loss) in global feature-based methods. Furthermore, a multi-level metric learning network (MMLN) is proposed for fine-grained image classification based on global features. In the MMLN, multi-level metric learning objectives and classification objectives are present at multiple high-level layers. The multi-level metric learning objectives work together to supervise the network in order to learn highly discriminative features. In addition, a new probability aggregation strategy (PAS) is proposed to produce a fused prediction by combining the multi-level predictive probabilities. Experiments were conducted on three standard fine-grained classification datasets (CUB-200-2011, Stanford Cars, and FGVC-Aircraft). Results demonstrated that our MMLN achieved accuracies of 88.0%, 94.6% and 92.4% respectively and outperformed state-of-the-art methods, substantially improving fine-grained classification tasks. Besides, gradient-weighted class activation mapping (Grad-CAM) shows that the MMLN is able to pay more attention to the discriminative local regions due to the application of multi-level metric learning.

1 November 2020
Verified
Conference Paper
Open access
YZYunxiang Zhao
Yunxiang Zhao
QKQiuhong Ke
Qiuhong Ke
FKFlip Korn
Flip Korn
JQJianzhong Qi
Jianzhong Qi
RZRui Zhang
Rui Zhang
Hexagonal CNN models have shown superior performance in applications such as IACT data analysis and aerial scene classification due to their better rotation symmetry and reduced anisotropy. In order to realize hexagonal processing, existing studies mainly use the ZeroOut method to imitate hexagonal processing, which causes substantial memory and computation overheads. We address this deficiency with a novel native hexagonal CNN framework named HexCNN. HexCNN takes hexagon-shaped input and performs forward and backward propagation on the original form of the input based on hexagon-shaped filters, hence avoiding computation and memory overheads caused by imitation. For applications with rectangle-shaped input but require hexagonal processing, HexCNN can be applied by padding the input into hexagon-shape as preprocessing. In this case, we show that the time and space efficiency of HexCNN still outperforms existing hexagonal CNN methods substantially. Experimental results show that compared with the state-of-the-art models, which imitate hexagonal processing but using rectangle-shaped filters, HexCNN reduces the training time by up to 42.2%. Meanwhile, HexCNN saves the memory space cost by up to 25% and 41.7% for loading the input and performing convolution, respectively.

29 July 2020 in IEEE Access
Verified
Journal Article
Open access
YYYixin Yang
Yixin Yang
YLYang Li
Yang Li
RZRui Zhang
Rui Zhang
JWJiabao Wang
Jiabao Wang
ZMZhuang Miao
Zhuang Miao
Making machines learn like humans is the ultimate goal of artificial intelligence. Few-shot learning attempts to simulate the learning mechanism of humans, which is a task that can learn novel concepts from very few labeled samples. Due to the lack of sufficient labeled training data, existing methods often increase the risk of over-fitting or cause a considerable gap between clean and augmented data. To solve these problems, we present a novel compare network to perform robust few-shot learning in a meta-learned end-to-end manner. Specifically, we argue that it is desirable to learn a robust encoder that can draw inferences about other cases from one example. To this end, we improve the accuracy of few-shot learning by mining the internal mechanism of deep networks, which can leverage label information more effectively. By introducing shift-invariant blocks and a self-attention block in our architecture, all these components are seamlessly integrated into our framework, which can give feedback to each other without data augmentation. Furthermore, we provide ablative analyses of different blocks to help understand how each term contributes to performance. Extensive experiments demonstrate that our method can provide more robust results and outperform state-of-the-art few-shot learning methods.

22 April 2025 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
YCYao Chen
Yao Chen
JWJiabao Wang
Jiabao Wang
PWPeichao Wang
Peichao Wang
RZRui Zhang
Rui Zhang
YLYang Li
Yang Li
Low-resolution fine-grained image classification has recently made significant progress, largely thanks to the superresolution techniques and knowledge distillation methods. However, these approaches lead to an exponential increase in the number of parameters and computational complexity of models. In order to solve this problem, in this letter, we propose a Vision Mamba Distillation (ViMD) approach to enhance the effectiveness and efficiency of low-resolution fine-grained image classification. Concretely, a lightweight super-resolution vision Mamba classification network (SRVM-Net) is proposed to improve its capability for extracting visual features by redesigning the classification sub-network with Mamba modeling. Moreover, we design a novel multi-level Mamba knowledge distillation loss boosting the performance, which can transfer prior knowledge obtained from a High-resolution Vision Mamba classification Network (HRVMNet) as a teacher into the proposed SRVM-Net as a student. Extensive experiments on seven public fine-grained classification datasets related to benchmarks confirm our ViMD achieves a new state-of-the-art performance. While having higher accuracy, ViMD outperforms similar methods with fewer parameters and FLOPs, which is more suitable for embedded device applications. Code is available at Github.