Mutual Supervision Research Articles

Compensation Mechanism for Ecological Diversity Governance in Chinese River Basins Application Based on Low-Carbon Water Quality Game Theory

Background: Taking the construction of ecological civilization as an important core of the overall layout of the “Five in One” and the coordinated promotion of the “Four Comprehensives” strategic layout, combined with the global concept of ecological environment governance, provides a new direction for the reform and innovation of China’s watershed ecological compensation system through diversified governance. Subjects and methods: This article focuses on ecological compensation in river basins, exploring collaborative cooperation models between upstream and downstream of the basin under the dual constraints of “low-carbon” and “water quality”, to achieve a “win-win” situation between the ecological environment of the basin and all parties involved in basin protection. Based on the theory of evolutionary game theory, the indicators of “carbon emissions” and “water quality” are introduced to construct a diversified ecological co-governance compensation strategy model for the watershed. By exploring the optimal strategies among various entities in the upstream and downstream of the watershed. Results: (1) In the initial stage, the optimal strategy for ecological compensation in the watershed among stakeholders cannot achieve a stable balance through their evolution; (2) In the mature stage, based on the regulation of the superior government, interest subjects will choose a mutual supervision strategy to avoid bearing high penalties, to achieve Pareto effectiveness in achieving a stable overall economy of the basin; (3) By paying for high-quality resources from downstream and implementing carbon trading among basin entities, we can promote internal resource digestion, reduce intermediate transaction costs, and deeply promote the overall green and sustainable development of the basin. Through analysis, it has been proven that the conclusion is effective, providing decision support for the diversified co-governance of watershed ecosystems. Based on building an ecological community with a shared future in the watershed, we aim to achieve the construction of a community with a shared future for mankind.

Misalignment-resistant domain adaptive learning for one-stage object detection

Without consideration of task specificity, directly transforming domain adaptive pipelines from classification to one-stage detection tends to pose severer misalignments. These misalignments include: (1) Foreground misalignment that the domain discriminator obsessively concentrates on backgrounds since one-stage detectors do not contain proposals for instance-level discrimination. (2) Localization misalignment that domain-adaptive features supervised by the domain discriminator are not suitable for localization tasks, as the discriminator is a classifier in essence. To tackle these problems, we propose the Misalignment-Resistant Domain Adaption (MRDA) for one-stage detectors. Specifically, to alleviate foreground misalignment, a mask-based domain discriminator is proposed to perform instance-level discrimination by assigning the pixel-level domain labels based on instance-level masks. As for localization misalignment, a localization discriminator is introduced to learn domain-adaptive features for localization tasks. It employs an additional box-regression branch with an IoU loss to perform adversarial mutual supervision with the feature extractor. Comprehensive experiments demonstrate that our method effectively mitigates the misalignments and achieves state-of-the-art detection across multiple datasets.

Semi-Supervised Interior Decoration Style Classification with Contrastive Mutual Learning

Precisely identifying interior decoration styles holds substantial significance in directing interior decoration practices. Nevertheless, constructing accurate models for the automatic classification of interior decoration styles remains challenging due to the scarcity of expert annotations. To address this problem, we propose a novel pseudo-label-guided contrastive mutual learning framework (PCML) for semi-supervised interior decoration style classification by harnessing large amounts of unlabeled data. Specifically, PCML introduces two distinct subnetworks and selectively utilizes the diversified pseudo-labels generated by each for mutual supervision, thereby mitigating the issue of confirmation bias. For labeled images, the inconsistent pseudo-labels generated by the two subnetworks are employed to identify images that are prone to misclassification. We then devise an inconsistency-aware relearning (ICR) regularization model to perform a review training process. For unlabeled images, we introduce a class-aware contrastive learning (CCL) regularization to learn their discriminative feature representations using the corresponding pseudo-labels. Since the use of distinct subnetworks reduces the risk of both models producing identical erroneous pseudo-labels, CCL can reduce the possibility of noise data sampling to enhance the effectiveness of contrastive learning. The performance of PCML is evaluated on five interior decoration style image datasets. For the average AUC, accuracy, sensitivity, specificity, precision, and F1 scores, PCML obtains improvements of 1.67%, 1.72%, 3.65%, 1.0%, 4.61%, and 4.66% in comparison with the state-of-the-art method, demonstrating the superiority of our method.

Dynamic Byzantine Fault-Tolerant Consensus Algorithm with Supervised Feedback Mechanisms

Among the existing consensus algorithms, there are very few low-latency consensus algorithms that can simultaneously take into account node dynamics, fault tolerance, and scalability, and which are applicable to large-scale open scenarios where low latency is required. Therefore, this paper proposes a low-latency scalable dynamic consensus algorithm with high fault tolerance utilizing a combination of layered and threshold signature technologies, known briefly as LTSBFT. Firstly, LTSBFT achieves linear communication complexity through the utilization of threshold signature technology and a two-layer structure. Secondly, the mutual supervision feedback mechanism among nodes enables the attainment of linear complexity for reaching consensus on the faulty upper-layer nodes during the view-change. Lastly, a node dynamic protocol was proposed for the first time to support dynamic changes in the number of nodes during the consensus process. That is to say, consensus can still be reached when the number of nodes dynamically changes without interrupting the client’s request for consensus in the network. The experimental results indicate that LTSBFT exhibits lower communication latency and higher throughput compared to the classic HotStuff and PBFT algorithms. Furthermore, in comparison to double-layer PBFT, the LTSBFT has been demonstrated to have improved fault tolerance.

Study on the Influences of Inter-Governmental Information Flow and Interdepartmental Collaborative Supervision on Pork Quality: A Case Study in China.

To study the influences of the degree of interdepartmental collaborative supervision on the behavioral strategy selection of pig farmers, pig slaughterers, and pork processing manufacturers in the pork supply chain system, this study established a three-party evolutionary game model involving pig farmers, pig slaughterers, and pork processing manufacturers based on the social co-governance framework by focusing on the interdepartmental information sharing mechanism and cooperative governance. Here, we examined how the degree of collaborative supervision among government departments influences the behavioral strategy selection of these parties by focusing on key mechanisms such as information sharing and interdepartmental collaborative governance. Our findings revealed that within a social co-governance system, the strategic choices of the three entities in the pork supply chain closely correlate with the coordination level of collaborative supervision among government departments, particularly through information-sharing mechanisms. Additionally, the strategies are influenced by market-based contract supervision among entities, consumer reporting intensity, and the collaborative governance capabilities of the government, market actors, and consumers. Higher levels of social co-governance are associated with fewer risky links in the pork supply chain and reduced overall risk. Key factors affecting the behavioral strategy selection of the subjects in the pork supply chain include interdepartmental collaborative governance among government departments (e.g., optimizing random inspection frequencies, adjusting economic penalties, and disclosing enterprise market credit information via information sharing mechanisms), consumer complaint probabilities, and the intensity of mutual supervision among enterprises. Therefore, to enhance pork supply chain quality and mitigate risks, it is crucial to enhance the coordination of collaborative supervision among government departments, encourage consumer reporting, and improve market-based mutual supervision mechanisms among upstream and downstream subjects in the supply chain.

Infrared and visible image fusion and detection based on interactive training strategy and feature filter extraction module

The infrared and visible image fusion-detection technique aims to expand the observation wavelength range to overcome harsh environmental conditions such as low light, smoke, heavy fog, etc., and improve the reliability and robustness of target detection. However, the current fusion-detection method suffers from problems of the joint optimization of the fusion-detection model and irrelevant feature interference. To address these problems, we propose an infrared and visible image fusion-detection network based on an interactive training strategy (ITS) and a feature filter extraction module (FFEM). The ITS constructs the closed-loop optimization for the fusion-detection method, which can mutually enhance the performance of the fusion and detection model through mutual supervision. The FFEM is designed to acquire detection-conducive features from visible and infrared images. Specifically, we define filtering weights based on the covariance values of features and use these weights to enhance relevant features and soft redundant and irrelevant features (e.g., noise). Quantitative and qualitative experimental results demonstrate that the proposed method achieves competitive performance in target detection accuracy compared with other state-of-the-art fusion-detection methods.

LMACL: Improving Graph Collaborative Filtering with Learnable Model Augmentation Contrastive Learning

Graph collaborative filtering (GCF) has achieved exciting recommendation performance with its ability to aggregate high-order graph structure information. Recently, contrastive learning (CL) has been incorporated into GCF to alleviate data sparsity and noise issues. However, most of the existing methods employ random or manual augmentation to produce contrastive views that may destroy the original topology and amplify the noisy effects. We argue that such augmentation is insufficient to produce the optimal contrastive view, leading to suboptimal recommendation results. In this article, we proposed a L earnable M odel A ugmentation C ontrastive L earning (LMACL) framework for recommendation, which effectively combines graph-level and node-level collaborative relations to enhance the expressiveness of collaborative filtering (CF) paradigm. Specifically, we first use the graph convolution network (GCN) as a backbone encoder to incorporate multi-hop neighbors into graph-level original node representations by leveraging the high-order connectivity in user-item interaction graphs. At the same time, we treat the multi-head graph attention network (GAT) as an augmentation view generator to adaptively generate high-quality node-level augmented views. Finally, joint learning endows the end-to-end training fashion. In this case, the mutual supervision and collaborative cooperation of GCN and GAT achieves learnable model augmentation. Extensive experiments on several benchmark datasets demonstrate that LMACL provides a significant improvement over the strongest baseline in terms of Recall and NDCG by 2.5%–3.8% and 1.6%–4.0%, respectively. Our model implementation code is available at https://github.com/LiuHsinx/LMACL .

Evaluation and threshold-based mutual supervision promotes the evolution of cooperation on interdependent networks

Inspired by the pivotal role of supervision mechanisms in promoting and maintaining cooperative behavior in human society, we propose a mutual supervision mechanism to explore the evolution of cooperation on an interdependent network. The mechanism adjusts the game type of supervised nodes when their evaluation value falls below a critical threshold. Monte Carlo simulations reveal that the mutual supervision mechanism effectively encourages the emergence of cooperative strategies on interdependent networks. The experimental results show a direct positive linkage between the number of supervised nodes and the fraction of cooperation. In detail, the effect of the sucker's payoff on cooperation is more noticeable when most of the nodes are supervised by the mechanism. However, a higher sucker's payoff discourages cooperation when there are few supervised nodes. Furthermore, the stability of cooperation is closely related to a stricter supervision threshold. Conversely, if the supervision threshold is too lenient, previously stable cooperation levels will suddenly collapse.

Unified structure-aware feature learning for Graph Convolutional Network

Graph Convolutional Network (GCN), as an effective technique for processing graph-structural data, has been widely used in various fields. Label Propagation Algorithm (LPA), also used as a way for message passing on a graph, broadcasts and integrates node labels over the edges. There have been several efforts to explore the joint learning of GCN and LPA for semi-supervised classification tasks. However, they fail to consider the following two points: (1) Capture precise connections and dispel heterophilous relationships between nodes under the mutual supervision of feature and label spaces; (2) Exploit high-order information so that it has varied weight values in affecting distinct nodes. In light of this, we propose a joint framework called structure-aware feature learning for graph convolutional network, which simultaneously takes into account the above two aspects. In specific, the proposed model consists of two modules: feature aggregation and label propagation, aiming to better utilize the information from both label and feature spaces to learn more accurate node representations. As a result, two modules interact with each other to flexibly assign edge weights. Meanwhile, we adopt a structure-aware manner to provide various weights for neighbors of each order of the target node, contributing to optionally capturing high-order information. Experiments indicate that the proposed method outperforms other compared semi-supervised classification models.

A variational expectation-maximization framework for balanced multi-scale learning of protein and drug interactions

Protein functions are characterized by interactions with proteins, drugs, and other biomolecules. Understanding these interactions is essential for deciphering the molecular mechanisms underlying biological processes and developing new therapeutic strategies. Current computational methods mostly predict interactions based on either molecular network or structural information, without integrating them within a unified multi-scale framework. While a few multi-view learning methods are devoted to fusing the multi-scale information, these methods tend to rely intensively on a single scale and under-fitting the others, likely attributed to the imbalanced nature and inherent greediness of multi-scale learning. To alleviate the optimization imbalance, we present MUSE, a multi-scale representation learning framework based on a variant expectation maximization to optimize different scales in an alternating procedure over multiple iterations. This strategy efficiently fuses multi-scale information between atomic structure and molecular network scale through mutual supervision and iterative optimization. MUSE outperforms the current state-of-the-art models not only in molecular interaction (protein-protein, drug-protein, and drug-drug) tasks but also in protein interface prediction at the atomic structure scale. More importantly, the multi-scale learning framework shows potential for extension to other scales of computational drug discovery.

Improving The Quality Of Catchment Area Model Public Services Based On Governance 4.0

This research is to examine Public Service Improvement using the Cathcment Area model based on governance 4.0. The implementation of e-government has experienced challenges since the growth of the industrial era 4.0. The development of technology is so rapid and unstoppable. Digitalisation is starting to enter the cracks of our daily lives. The Catchment Area perspective in this study is an important factor to see the efficiency and effectiveness of services to the community in local government administration based on governance 4.0. The research locus is Sidoarjo Regency. This research uses a qualitative approach. Research focus (1). Identifying factors that affect service quality. Research Results: factors that can affect the catchment area include the function of the region on the condition of the regional economy and also the national economy which is unique in nature, tax sources that can be explored potentially and in real terms to be able to achieve balance between various regions, the efficiency and effectiveness of services to the community in an area that is seen based on the optimal area for the service itself, participation that can be achieved effectively and mutual supervision between citizens and local bureaucracy.

A Study on the Construction of Cultural Identity of Chinese Students Studying Abroad under the "Belt and Road" Initiative

The great rejuvenation of the Chinese nation and the implementation of the Belt and Road Initiative, a centennial plan, are significantly displaying Chinese civilization worldwide. The dissemination of civilization is merely a process, while the recognition of civilization enables the world to breathe in unison with China, share a common destiny, and connect hearts and minds. The alignment of people's hearts and minds is achieved through righteousness and justice. In this context, how to promote China and gain global recognition is one of the core tasks of China's diplomacy, united front work, and the long-term implementation of the Belt and Road strategy. International students coming to China for study are an important force in spreading Chinese civilization, values, and the Chinese model to the outside world. While imparting scientific and cultural knowledge, schools need to conduct implicit cultural education to establish correct values and worldviews. It is essential to cultivate international students' recognition of Chinese culture, Chinese territory, and the path of development with Chinese characteristics. The aim is to ignite a spark that can start a prairie fire, laying a foundation for building a friendship of "long-term coexistence, mutual supervision, mutual trust, and shared honor and disgrace" between China and the world in the future.

Multi-input mutual supervision network for single-pixel computational imaging

In this study, we propose a single-pixel computational imaging method based on a multi-input mutual supervision network (MIMSN). We input one-dimensional (1D) light intensity signals and two-dimensional (2D) random image signal into MIMSN, enabling the network to learn the correlation between the two signals and achieve information complementarity. The 2D signal provides spatial information to the reconstruction process, reducing the uncertainty of the reconstructed image. The mutual supervision of the reconstruction results for these two signals brings the reconstruction objective closer to the ground truth image. The 2D images generated by the MIMSN can be used as inputs for subsequent iterations, continuously merging prior information to ensure high-quality imaging at low sampling rates. The reconstruction network does not require pretraining, and 1D signals collected by a single-pixel detector serve as labels for the network, enabling high-quality image reconstruction in unfamiliar environments. Especially in scattering environments, it holds significant potential for applications.

Partial Label Learning with a Partner

In partial label learning (PLL), each instance is associated with a set of candidate labels among which only one is ground-truth. The majority of the existing works focuses on constructing robust classifiers to estimate the labeling confidence of candidate labels in order to identify the correct one. However, these methods usually struggle to rectify mislabeled samples. To help existing PLL methods identify and rectify mislabeled samples, in this paper, we introduce a novel partner classifier and propose a novel ``mutual supervision'' paradigm. Specifically, we instantiate the partner classifier predicated on the implicit fact that non-candidate labels of a sample should not be assigned to it, which is inherently accurate and has not been fully investigated in PLL. Furthermore, a novel collaborative term is formulated to link the base classifier and the partner one. During each stage of mutual supervision, both classifiers will blur each other's predictions through a blurring mechanism to prevent overconfidence in a specific label. Extensive experiments demonstrate that the performance and disambiguation ability of several well-established stand-alone and deep-learning based PLL approaches can be significantly improved by coupling with this learning paradigm.

UVAGaze: Unsupervised 1-to-2 Views Adaptation for Gaze Estimation

Gaze estimation has become a subject of growing interest in recent research. Most of the current methods rely on single-view facial images as input. Yet, it is hard for these approaches to handle large head angles, leading to potential inaccuracies in the estimation. To address this issue, adding a second-view camera can help better capture eye appearance. However, existing multi-view methods have two limitations. 1) They require multi-view annotations for training, which are expensive. 2) More importantly, during testing, the exact positions of the multiple cameras must be known and match those used in training, which limits the application scenario. To address these challenges, we propose a novel 1-view-to-2-views (1-to-2 views) adaptation solution in this paper, the Unsupervised 1-to-2 Views Adaptation framework for Gaze estimation (UVAGaze). Our method adapts a traditional single-view gaze estimator for flexibly placed dual cameras. Here, the "flexibly" means we place the dual cameras in arbitrary places regardless of the training data, without knowing their extrinsic parameters. Specifically, the UVAGaze builds a dual-view mutual supervision adaptation strategy, which takes advantage of the intrinsic consistency of gaze directions between both views. In this way, our method can not only benefit from common single-view pre-training, but also achieve more advanced dual-view gaze estimation. The experimental results show that a single-view estimator, when adapted for dual views, can achieve much higher accuracy, especially in cross-dataset settings, with a substantial improvement of 47.0%. Project page: https://github.com/MickeyLLG/UVAGaze.

Consistency-Guided Temperature Scaling Using Style and Content Information for Out-of-Domain Calibration

Research interests in the robustness of deep neural networks against domain shifts have been rapidly increasing in recent years. Most existing works, however, focus on improving the accuracy of the model, not the calibration performance which is another important requirement for trustworthy AI systems. Temperature scaling (TS), an accuracy-preserving post-hoc calibration method, has been proven to be effective in in-domain settings, but not in out-of-domain (OOD) due to the difficulty in obtaining a validation set for the unseen domain beforehand. In this paper, we propose consistency-guided temperature scaling (CTS), a new temperature scaling strategy that can significantly enhance the OOD calibration performance by providing mutual supervision among data samples in the source domains. Motivated by our observation that over-confidence stemming from inconsistent sample predictions is the main obstacle to OOD calibration, we propose to guide the scaling process by taking consistencies into account in terms of two different aspects - style and content - which are the key components that can well-represent data samples in multi-domain settings. Experimental results demonstrate that our proposed strategy outperforms existing works, achieving superior OOD calibration performance on various datasets. This can be accomplished by employing only the source domains without compromising accuracy, making our scheme directly applicable to various trustworthy AI systems.

TaiChiNet: Negative-Positive Cross-Attention Network for Breast Lesion Segmentation in Ultrasound Images.

Breast lesion segmentation in ultrasound images is essential for computer-aided breast-cancer diagnosis. To improve the segmentation performance, most approaches design sophisticated deep-learning models by mining the patterns of foreground lesions and normal backgrounds simultaneously or by unilaterally enhancing foreground lesions via various focal losses. However, the potential of normal backgrounds is underutilized, which could reduce false positives by compacting the feature representation of all normal backgrounds. From a novel viewpoint of bilateral enhancement, we propose a negative-positive cross-attention network to concentrate on normal backgrounds and foreground lesions, respectively. Derived from the complementing opposites of bipolarity in TaiChi, the network is denoted as TaiChiNet, which consists of the negative normal-background and positive foreground-lesion paths. To transmit the information across the two paths, a cross-attention module, a complementary MLP-head, and a complementary loss are built for deep-layer features, shallow-layer features, and mutual-learning supervision, separately. To the best of our knowledge, this is the first work to formulate breast lesion segmentation as a mutual supervision task from the foreground-lesion and normal-background views. Experimental results have demonstrated the effectiveness of TaiChiNet on two breast lesion segmentation datasets with a lightweight architecture. Furthermore, extensive experiments on the thyroid nodule segmentation and retinal optic cup/disc segmentation datasets indicate the application potential of TaiChiNet.

Mutual Supervision of MFL Heterogeneous Signals for Insufficient Sample Defect Detection on Pipeline Safety Operation

Mutual Supervision of MFL Heterogeneous Signals for Insufficient Sample Defect Detection on Pipeline Safety Operation

Fine-Grained Self-Supervision for Generalizable Semantic Segmentation

Unsupervised domain adaptative semantic segmentation is a powerful solution for the distribution shift problem between the source and target domains. However, such methods need specified target domain data that may be unavailable in actual applications due to excess expensive collection. Generalizable semantic segmentation as a new paradigm appears in recent research, which aims to generalize well on distinct unseen domains only using source domain data. The existing methods focus on learning domain-invariant features by using global distribution alignment strategies, which may lead to a decreased discriminability of the model. To cope with this challenge, we propose a fine-grained self-supervision (FGSS) framework for generalizable semantic segmentation that takes into account both discriminability and generalizability from the perspective of the intra-class relationship. The FGSS framework contains single-view and multi-view versions. In the single-view version, we propose a fine-grained self-supervision strategy to distinguish the sub-parts of the semantic class for better class discriminability. In the multi-view version, we propose a class prototype feature enhancement strategy to generate another view (i.e. another representation of the original representation). Then, we propose a multi-view mutual supervision loss to enforce consistency between different views and further enhance the generalizability of the model. Experimental results on five widely-used datasets, i.e., GTAV, SYNTHIA, BDD100K, Cityscapes, and Mapillary, demonstrate that our FGSS framework achieves superior performance compared to state-of-the-art methods.

Joint learning of motion deblurring and defocus deblurring networks with a real-world dataset

When recovering the sharp image from a blurry observation, moving objects, e.g., people and vehicles, usually attract more perceptual attention. However, existing motion deblurring methods primarily focus on removing the global camera motion blur, while neglecting the object motion blur. In this paper, we propose a joint learning framework for motion deblurring and defocus deblurring (JLMD), where a motion deblurring network can be trained for removing object motion blur, and a defocus deblurring network can be also obtained as a byproduct. Especially, we propose to circumvent the hardship in obtaining all-sharp ground truth for object motion blurry images by leveraging the complementary nature between object motion blur and defocus blur. The JLMD framework incorporates three key components. Firstly, a mask generation module is deployed to predict the boundary of motion blur. Secondly, a mutual supervision mechanism is elaborated, which enables the defocus blurry image and the motion blurry image to serve as the ground truth for each other. Thirdly, a content preservation loss is designed to encourage non-blurry regions to stay unchanged. Furthermore, we introduce a Defocus and Motion Deblurring Dataset (DMDD), which is the first real-world dataset specifically dedicated to object motion blurry images. Extensive experiments validate that our method is more effective in removing object motion blur than state-of-the-art methods, while it is at least comparable or superior in removing global camera motion blur and defocus blur. The source code and dataset are available at https://github.com/liyucs/JLMD.