Author name cluster

Zhihui Wang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

9 papers

1 author row

AAAI Conference 2025 Conference Paper

Towards Efficient and Intelligent Laser Weeding: Method and Dataset for Weed Stem Detection

Dingning Liu
Jinzhe Li
Haoyang Su
Bei Cui
Zhihui Wang
Qingbo Yuan
Wanli Ouyang
Nanqing Dong

Weed control is a critical challenge in modern agriculture, as weeds compete with crops for essential nutrient resources, significantly reducing crop yield and quality. Traditional weed control methods, including chemical and mechanical approaches, have real-life limitations such as associated environmental impact and efficiency. An emerging yet effective approach is laser weeding, which uses a laser beam as the stem cutter. Although there have been studies that use deep learning in weed recognition, its application in intelligent laser weeding still requires a comprehensive understanding. Thus, this study serves the first empirical study on weed recognition for laser weeding. To increase the efficiency of laser beam cut and avoid damaging the crops of interest, the laser beam shall be directly aimed at the weed root. Yet, weed stem detection remains an under-explored problem. We integrate the detection of crop and weed with the localization of weed stem into one end-to-end system. To train and validate the proposed system in a real-life scenario, we curate and construct a high-quality weed stem detection dataset with human annotations. The dataset consists of 7,161 high-resolution pictures collected in the field with annotations of 11,151 instances of weed. The dataset will be released upon acceptance. Experimental results show that, in contrast to seminal weed recognition systems, the proposed system can efficiently improve the weeding accuracy by 5.05% and reduce the energy cost by 32.3%.

PDF Details DOI

AIIM Journal 2024 Journal Article

HoRDA: Learning higher-order structure information for predicting RNA–disease associations

Julong Li
Jianrui Chen
Zhihui Wang
Xiujuan Lei

CircRNA and miRNA are crucial non-coding RNAs, which are associated with biological diseases. Exploring the associations between RNAs and diseases often requires a significant time and financial investments, which has been greatly alleviated and improved with the application of deep learning methods in bioinformatics. However, existing methods often fail to achieve higher accuracy and cannot be universal between multiple RNAs. Moreover, complex RNA–disease associations hide important higher-order topology information. To address these issues, we learn higher-order structure information for predicting RNA–disease associations (HoRDA). Firstly, the correlations between RNAs and the correlations between diseases are fully explored by combining similarity and higher-order graph attention network. Then, a higher-order graph convolutional network is constructed to aggregate neighbor information, and further obtain the representations of RNAs and diseases. Meanwhile, due to the large number of complex and variable higher-order structures in biological networks, we design a higher-order negative sampling strategy to gain more desirable negative samples. Finally, the obtained embeddings of RNAs and diseases are feed into logistic regression model to acquire the probabilities of RNA–disease associations. Diverse simulation results demonstrate the superiority of the proposed method. In the end, the case study is conducted on breast neoplasms, colorectal neoplasms, and gastric neoplasms. We validate the proposed higher-order strategies through ablative and exploratory analyses and further demonstrate the practical applicability of HoRDA. HoRDA has a certain contribution in RNA–disease association prediction.

Details DOI

EAAI Journal 2024 Journal Article

Relation mapping based on higher-order graph convolutional network for entity alignment

Luheng Yang
Jianrui Chen
Zhihui Wang
Fanhua Shang

Recently, entity alignment for building knowledge graphs (KGs) has gathered increasing interest in the field of knowledge engineering. Existing models that are based on translation embeddings and graph convolutional network (GCN) further promote quality of entity embeddings, but most of them fail to pay attention to the influence of higher-order neighbors. However, higher-order information is strikingly central to perform entity alignment. Although the introduction of relationships between entities can further enhance the alignment, the existing methods have poor quality for relation embeddings. To overcome the issues, we design a novel Relation Mapping based on Higher-order Graph Convolutional Network for entity alignment, named RMHN. Specifically, a novel higher-order GCN is designed to aggregate higher-order information to considerably obtain entity embeddings. Additionally, we design a new relational mapping mechanism to obtain relation embeddings, which can drastically assist in the alignment process. To unlock the critical bottleneck that the current sampling strategies do not substantially improve the performance of entity alignment, we propose a new adversarial sampling strategy. Finally, experimental results on benchmark datasets exhibit the RMHN model surprisingly outperforms the state-of-the-art models.

Details DOI

IJCAI Conference 2023 Conference Paper

Decoupling with Entropy-based Equalization for Semi-Supervised Semantic Segmentation

Chuanghao Ding
Jianrong Zhang
Henghui Ding
Hongwei Zhao
Zhihui Wang
Tengfei Xing
Runbo Hu

Semi-supervised semantic segmentation methods are the main solution to alleviate the problem of high annotation consumption in semantic segmentation. However, the class imbalance problem makes the model favor the head classes with sufficient training samples, resulting in poor performance of the tail classes. To address this issue, we propose a Decoupled Semi-Supervise Semantic Segmentation (DeS4) framework based on the teacher-student model. Specifically, we first propose a decoupling training strategy to split the training of the encoder and segmentation decoder, aiming at a balanced decoder. Then, a non-learnable prototype-based segmentation head is proposed to regularize the category representation distribution consistency and perform a better connection between the teacher model and the student model. Furthermore, a Multi-Entropy Sampling (MES) strategy is proposed to collect pixel representation for updating the shared prototype to get a class-unbiased head. We conduct extensive experiments of the proposed DeS4 on two challenging benchmarks (PASCAL VOC 2012 and Cityscapes) and achieve remarkable improvements over the previous state-of-the-art methods.

PDF Details DOI

EAAI Journal 2023 Journal Article

Delayed evolutionary game clustering-based recommendation algorithm via latent information and user preference

Jianrui Chen
Tingting Zhu
Qilao Zha
Zhihui Wang

Recommendation system is widely used because of its personalized service. It helps users obtain satisfactory results due to ambiguous expression in search engines. However, with the increasing number of users and items, most of the existing recommendation algorithms have problems of cold start, sparse data and high complexity. To address the above issues, this paper applies the rating information and attribute information of users and items to better represent the preferences of users and the activity of items by enriching the available information. Furthermore, we propose a novel game-based evolutionary clustering method to divide interest communities for users, which not only reduces the complexity of recommendation, but also takes full account of users’ preferences. In addition, the impact of delayed information transmission on experimental performance is considered in the game-based evolutionary clustering. Since the calculation of similarity plays a significant role in finding the nearest neighbors of target users in the community, we propose a new similarity measurement strategy based on user preferences. Finally, the effectiveness of the proposed algorithm is verified by ablation experiment and comparison experiments. The experimental results illustrate that our algorithm outperforms the existing excellent algorithms.

Details DOI

AAAI Conference 2023 Conference Paper

Fine-Grained Retrieval Prompt Tuning

Shijie Wang
Jianlong Chang
Zhihui Wang
Haojie Li
Wanli Ouyang
Qi Tian

Fine-grained object retrieval aims to learn discriminative representation to retrieve visually similar objects. However, existing top-performing works usually impose pairwise similarities on the semantic embedding spaces or design a localization sub-network to continually fine-tune the entire model in limited data scenarios, thus resulting in convergence to suboptimal solutions. In this paper, we develop Fine-grained Retrieval Prompt Tuning (FRPT), which steers a frozen pre-trained model to perform the fine-grained retrieval task from the perspectives of sample prompting and feature adaptation. Specifically, FRPT only needs to learn fewer parameters in the prompt and adaptation instead of fine-tuning the entire model, thus solving the issue of convergence to suboptimal solutions caused by fine-tuning the entire model. Technically, a discriminative perturbation prompt (DPP) is introduced and deemed as a sample prompting process, which amplifies and even exaggerates some discriminative elements contributing to category prediction via a content-aware inhomogeneous sampling operation. In this way, DPP can make the fine-grained retrieval task aided by the perturbation prompts close to the solved task during the original pre-training. Thereby, it preserves the generalization and discrimination of representation extracted from input samples. Besides, a category-specific awareness head is proposed and regarded as feature adaptation, which removes the species discrepancies in features extracted by the pre-trained model using category-guided instance normalization. And thus, it makes the optimized features only include the discrepancies among subcategories. Extensive experiments demonstrate that our FRPT with fewer learnable parameters achieves the state-of-the-art performance on three widely-used fine-grained datasets.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Learning to Parameterize Visual Attributes for Open-set Fine-grained Retrieval

Shijie Wang
Jianlong Chang
Haojie Li
Zhihui Wang
Wanli Ouyang
Qi Tian

Open-set fine-grained retrieval is an emerging challenging task that allows to retrieve unknown categories beyond the training set. The best solution for handling unknown categories is to represent them using a set of visual attributes learnt from known categories, as widely used in zero-shot learning. Though important, attribute modeling usually requires significant manual annotations and thus is labor-intensive. Therefore, it is worth to investigate how to transform retrieval models trained by image-level supervision from category semantic extraction to attribute modeling. To this end, we propose a novel Visual Attribute Parameterization Network (VAPNet) to learn visual attributes from known categories and parameterize them into the retrieval model, without the involvement of any attribute annotations. In this way, VAPNet could utilize its parameters to parse a set of visual attributes from unknown categories and precisely represent them. Technically, VAPNet explicitly attains some semantics with rich details via making use of local image patches and distills the visual attributes from these discovered semantics. Additionally, it integrates the online refinement of these visual attributes into the training process to iteratively enhance their quality. Simultaneously, VAPNet treats these attributes as supervisory signals to tune the retrieval models, thereby achieving attribute parameterization. Extensive experiments on open-set fine-grained retrieval datasets validate the superior performance of our VAPNet over existing solutions.

PDF Details

AAAI Conference 2022 Conference Paper

Category-Specific Nuance Exploration Network for Fine-Grained Object Retrieval

Shijie Wang
Zhihui Wang
Haojie Li
Wanli Ouyang

Employing additional prior knowledge to model local features as a final fine-grained object representation has become a trend for fine-grained object retrieval (FGOR). A potential limitation of these methods is that they only focus on common parts across the dataset (e. g. , head, body, or even leg) by introducing additional prior knowledge, but the retrieval of a fine-grained object may rely on category-specific nuances that contribute to category prediction. To handle this limitation, we propose an end-to-end Category-specific Nuance Exploration Network (CNENet) that elaborately discovers category-specific nuances that contribute to category prediction, and semantically aligns these nuances grouped by subcategory without any additional prior knowledge, to directly emphasize the discrepancy among subcategories. Specifically, we design a Nuance Modelling Module that adaptively predicts a group of category-specific response (CARE) maps via implicitly digging into category-specific nuances, specifying the locations and scales for category-specific nuances. Upon this, two nuance regularizations are proposed: 1) semantic discrete loss that forces each CARE map to attend to different spatial regions to capture diverse nuances; 2) semantic alignment loss that constructs a consistent semantic correspondence for each CARE map of the same order with the same subcategory via guaranteeing each instance and its transformed counterpart to be spatially aligned. Moreover, we propose a Nuance Expansion Module, which exploits context appearance information of discovered nuances and refines the prediction of current nuance by its similar neighbors, leading to further improvement on nuance consistency and completeness. Extensive experiments validate that our CNENet consistently yields the best performance under the same settings against most competitive approaches on CUB Birds, Stanford Cars, and FGVC Aircraft datasets.

PDF Details

AAAI Conference 2021 Conference Paper

Dynamic Position-aware Network for Fine-grained Image Recognition

Shijie Wang
Haojie Li
Zhihui Wang
Wanli Ouyang

Most weakly supervised fine-grained image recognition (WF- GIR) approaches predominantly focus on learning the discriminative details which contain the visual variances and position clues. The position clues can be indirectly learnt by utilizing context information of discriminative visual content. However, this will cause the selected discriminative regions containing some non-discriminative information introduced by the position clues. These analysis motivates us to directly introduce position clues into visual content to only focus on the visual variances, achieving more precise discriminative region localization. Though important, position modelling usually requires significant pixel/region annotations and therefore is labor-intensive. To address this issue, we propose an end-to-end Dynamic Position-aware Network (DP-Net) to directly incorporate the position clues into visual content and dynamically align them without extra annotations, which eliminates the effect of position information for discriminative variances among subcategories. In particular, the DP-Net consists of: 1) Position Encoding Module, which learns a set of position-aware parts by directly adding the learnable position information into the horizontal/vertical visual content of images; 2) Position-vision Aligning Module, which dynamically aligns both visual content and learnable position information via performing graph convolution on position-aware parts; 3) Position-vision Reorganization Module, which projects the aligned position clues and visual content into the Euclidean space to construct a position-aware feature maps. Finally, the position-aware feature maps are used which is implicitly applied the aligned visual content and position clues for more accurate discriminative regions localization. Extensive experiments verify that DP-Net yields the best performance under the same settings with most competitive approaches, on CUB Bird, Stanford-Cars, and FGVC Aircraft datasets.

PDF Details