In semi-supervised medical image segmentation, the scarcity of labeled data makes models prone to learning bias, causing persistent errors in certain regions and eventual over-fitting, significantly impacting segmenta...
详细信息
ISBN:
(数字)9798350390155
ISBN:
(纸本)9798350390162
In semi-supervised medical image segmentation, the scarcity of labeled data makes models prone to learning bias, causing persistent errors in certain regions and eventual over-fitting, significantly impacting segmentation performance. These problematic regions, termed difficult areas, are inadequately addressed by existing methods. To address this, We propose the Difficulty Perception-Processing Heterogeneous Network (DPP-Net). It guides the model in accurately perceiving and rectifying difficult areas, overcoming learning bias. Specifically, we introduce the Global Mutual Perception (GMP) to establish a comprehensive information perception channel between sample data, enabling a more holistic and accurate perception of difficult areas. The Difficulty-Aware Rectification (DAR) structure ensures continuous monitoring of difficult areas during training, allowing for timely adjustments to errors. Additionally, the Adaptive Competitive Pseudo-Label (ACP) Augmentation strategy enhances pseudo-labels through adaptive confidence competition. Experimental results on two different medical image databases (CT and MRI) demonstrate that our approach outperforms several state-of-the-art methods.
While graph neural networks (GNNs) have become the de facto standard for graph-based node classification, they impose a strong assumption on the availability of sufficient labeled samples. This assumption restricts th...
详细信息
While graph neural networks (GNNs) have become the de facto standard for graph-based node classification, they impose a strong assumption on the availability of sufficient labeled samples. This assumption restricts the classification performance of prevailing GNNs on many real-world applications suffering from low-data regimes. Specifically, features extracted from scarce labeled nodes could not provide sufficient supervision for the unlabeled samples, leading to severe overfitting. We point out that leveraging subgraphs to capture long-range dependencies can augment the node representation, thus alleviating the low-data regime. To this end, we present a novel self-supervised learning (SSL) framework, called multiview subgraph neural networks (Muse), for handling the long-range dependencies. In particular, we propose an information theory-based identification mechanism to identify two types of subgraphs from the views of input space and latent space, respectively. The former is to capture the local structure of the graph, while the latter captures the long-range dependencies among nodes. By fusing these two views of subgraphs, the learned representations can preserve the topological properties of the graph at large, including the local structure and long-range dependencies, thus maximizing their expressiveness. Theoretically, we provide the generalization error bound to show the effectiveness of capturing complementary information from multiview subgraphs. Empirically, we show a proof-of-concept of Muse on canonical node classification problems on graph data.
Fusing a hyperspectral image (HSI) with a multispectral image (MSI) to produce a super-resolution image (SRI) that possesses both fine spatial and spectral resolutions is a widely adopted technique in hyperspectral su...
Fusing a hyperspectral image (HSI) with a multispectral image (MSI) to produce a super-resolution image (SRI) that possesses both fine spatial and spectral resolutions is a widely adopted technique in hyperspectral super-resolution (HSR). Most existing HSR methods accomplish this task within the framework of linear mixing model (LMM). However, a severe challenge lies in the inherent linear constraint of LMM, which hinders the adaptability of these HSR methods to complex real-world scenarios. In this work, the LMM is extended to the generalized bilinear model (GBM), and a novel HSR method based on nonnegative tensor factorization is proposed in the framework of nonlinear unmixing. Apart from the linear part, it additionally considers the main nonlinear interactions, that is, the bilinear interactions between the endmembers. Crucially, each potential decomposition factor possesses a physical interpretation, enabling the incorporation of prior information to enhance reconstruction performance. Furthermore, an HSR algorithm has been devised specifically for scenarios where the spatial degradation operators from SRI to HSI are unknown, which undoubtedly enhances its practical applicability. The proposed methods overcome the inherent linear limitations of the LMM framework while avoiding the information loss associated with matrixizing HSI and MSI. The effectiveness of the proposed methods is showcased through simulated and real data.
Self-supervised pre-training followed by fine-tuning is a potent paradigm for few-shot learning, leveraging extensive unlabeled data with remarkable efficacy. Current self-supervised methods often lean towards Vision ...
详细信息
ISBN:
(数字)9798350386226
ISBN:
(纸本)9798350386233
Self-supervised pre-training followed by fine-tuning is a potent paradigm for few-shot learning, leveraging extensive unlabeled data with remarkable efficacy. Current self-supervised methods often lean towards Vision Transformers (ViTs) rather than CNN-Transformer hybrid architectures, which generally demonstrate superior performance. However, this reliance on ViTs can lead to poor perception of local features by the model. The challenge lies in designing a suitable proxy task for hybrid architectures like CNN-Transformers, which have significant structural differences. Additionally, the current organization of CNN-Transformer hybrid backbones is often sequential, hindering collaboration during pre-training and the acquisition of robust representations. To address these issues, we propose Self-Supervised Collaborative CNN-Transformer (S
2
CCT) for few-shot medical image segmentation. This framework introduces three innovative designs: (1) a composite proxy task based on image masking and image super-resolution tailored for CNN-Transformer hybrid architectures, enabling the backbone to acquire robust representations during pre-training that can be transferred to downstream tasks; (2) a parallel CNN-Transformer architecture that better attends to multi-scale features in images, making it more suitable for dense prediction tasks like image segmentation; (3) a sparse and dense feature fusion module to enhance collaboration between the two encoders. Experiments demonstrate that S
2
CCT outperforms previous state-of-the-art methods on two public medical image segmentation benchmarks, i.e., ACDC and KiTs19. The code and pretrained models will be released soon.
This paper fills a gap in urban sewage treatment decision-making by exploring reward and punishment mechanisms within the uncertainty theory framework. Addressing challenges in characterizing sewage treatment capacity...
详细信息
Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely...
ISBN:
(纸本)9798331314385
Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely, diffusion feature. We discover that diffusion feature has been hindered by a hidden yet universal phenomenon that we call content shift. To be specific, there are content differences between features and the input image, such as the exact shape of a certain object. We locate the cause of content shift as one inherent characteristic of diffusion models, which suggests the broad existence of this phenomenon in diffusion feature. Further empirical study also indicates that its negative impact is not negligible even when content shift is not visually perceivable. Hence, we propose to suppress content shift to enhance the overall quality of diffusion features. Specifically, content shift is related to the information drift during the process of recovering an image from the noisy input, pointing out the possibility of turning off-the-shelf generation techniques into tools for content shift suppression. We further propose a practical guideline named GATE to efficiently evaluate the potential benefit of a technique and provide an implementation of our methodology. Despite the simplicity, the proposed approach has achieved superior results on various tasks and datasets, validating its potential as a generic booster for diffusion features. Our code is available at https://***/Darkbblue/diffusion-content-shift.
Dynamic Constrained Multiobjective Optimization Problems (DCMOPs) are characterized by multiple conflicting optimization objectives and constraints that vary over time. The presence of both dynamism and constraints un...
详细信息
Dynamic Constrained Multiobjective Optimization Problems (DCMOPs) are characterized by multiple conflicting optimization objectives and constraints that vary over time. The presence of both dynamism and constraints underscores the importance of preserving population diversity. This diversity is essential not only to escape local optima following environmental changes but also to climb infeasible barriers to approach feasible regions. However, existing constraint-handling techniques for enhancing solution feasibility could steer infeasible solutions toward partially feasible regions, potentially resulting in the loss of diversity. To maintain both diversity and feasibility, this work establishes two synergistic tasks: one task concentrates on exploring the unconstrained search space to preserve diversity, while the other delves into searching the constrained search space to prioritize feasibility. Particularly, in light of evolutionary transfer optimization, two knowledge transfer modules, i.e., the spatial knowledge transfer module and temporal knowledge transfer module are designed. The spatial knowledge transfer module facilitates knowledge transfer between the constrained and unconstrained search spaces to accelerate the exploration of both spaces. On the other hand, the temporal transfer module leverages historical knowledge to enhance search efficiency within the new environment. To advance the test suite toward real-world cases, we designed fourteen test problems with various properties. Experiments conducted on the proposed test problems and a real-world problem have demonstrated the efficacy of our proposed algorithm. IEEE
Probabilistic electricity price forecasting (EPF) is paramount for stakeholder scheduling and trading in deregulated energy markets. However, during the process of establishing a probability prediction model, the cons...
详细信息
Heterogeneous information networks (HINs) have become a popular tool to capture complicated user-item relationships in recommendation problems in recent years. As a typical instantiation of HINs, meta-path is introduc...
详细信息
In reasoning tasks, even a minor error can cascade into inaccurate results, leading to suboptimal performance of large language models in such domains. Earlier fine-tuning approaches sought to mitigate this by leverag...
详细信息
暂无评论