Existing multi-organ segmentation methods usually rely on large and fully labeled datasets for training. However, medical image datasets are typically decentralized by privacy constraints and partially labeled due to the high costs of full annotation in clinical practice, resulting in label inconsistency across medical centers. Federated learning offers privacy-preserving decentralized training, but the label inconsistency leads to significant divergence in local model parameters across medical centers, thereby hindering the achievement of the global optimum. To resolve this issue, an effective and communication-efficient Federated Learning under Reliable Supervision (FedRS) is proposed, which ensures: i) the local models are trained with reliable supervisory information through the proposed Less-Forgetting and Less-Constraint loss functions, thereby reducing the divergence in local model parameters; and ii) the global model is aggregated based on the consistency of predictions between each local model (after local training) and the global model (received before training), thereby enhancing the reliability of the global model. Extensive experimental results on nine publicly available 3D abdominal CT image datasets show that our FedRS outperforms localized, centralized, and state-of-the-art federated learning methods on both in-federation and out-of-federation datasets, demonstrating its effectiveness and strong generalization capability. In particular, our FedRS only utilizes a model with only 4.1M parameters as its backbone, thereby significantly reducing its communication cost. The source code is publicly available at https://github.com/luohy812/FedRS.

Federated Class Incremental Learning (FCIL) enables distributed clients to collaboratively train a global model based on their private sequential tasks without compromising data privacy. Currently, some FCIL methods have been proposed, and most are designed based on deep models. However, enabling these FCIL models to converge requires numerous communication rounds, significantly increasing communication costs. Recently, the Broad Learning System (BLS), an effective and efficient shallow model, was proposed and adapted for CIL tasks [i.e., BLS-Class Incremental Learning (CIL)]. BLS-CIL exhibits fast updates and high retainability. However, it requires prior knowledge of when new class data arrives and cannot be directly used in federated scenarios due to the global catastrophic forgetting in FCIL. Thus, an innovative Federated Class incremental learning method based on BLS (FedCBLS) is proposed, which extends BLS-CIL within the federated scenario and provides three advantages: 1) high accuracy from the local perspective, achieved by integrating BLS-CIL with a newly designed automatic decision-making (ADM) method to detect novel classes and learn them incrementally for local clients; 2) high accuracy from the global perspective, attained through the newly proposed local model refinement (LMR) and global model projection (GMP) methods, mitigating global catastrophic forgetting stemming from heterogeneous data across clients; and 3) extremely low communication costs due to the newly derived closed-form solutions without iterative optimization for both local and global models. Comprehensive experimental results show that our FedCBLS outperforms the state-of-the-art (SOTA) FCIL methods by up to 8.15%, while drastically reducing communication costs to 1% of SOTA’s. Our code is available athttps://github.com/dujie-szu/FedCBLS.git

Class activation mapping (CAM) methods have garnered considerable research attention because they can be used to interpret the decision-making of deep convolutional neural network (CNN) models and provide initial masks for weakly supervised semantic segmentation (WSSS) tasks. However, the class activation maps generated by most CAM methods usually have two limitations: 1) a lack of the ability to cover the whole object when using low-level features; and 2) introducing background noise. To mitigate these issues, an innovative Context-level weights-based CAM (Context-CAM) method is proposed, which guarantees: 1) the non-discriminative regions that have similar appearances and are located close to the discriminative regions can also be highlighted by the newly designed Region-Enhanced Mapping (REM) module using context-level weights; and 2) the background noises are gradually eliminated via a newly proposed Semantic-guided Reverse Sequence Fusion (SRSF) strategy that can sequentially denoise and fuse the region-enhanced maps from the last layer to the first layer. Extensive experimental results show that our Context-CAM can generate higher-quality class activation maps than classic and state-of-the-art (SOTA) CAM methods in terms of the Energy-Based Pointing Game (EBPG) score, and the improvements are up to 35.49% when compared to the second-best method. Moreover, for WSSS tasks, our Context-CAM can directly replace the CAM method used in existing WSSS methods without any architectural modification to further improve the segmentation performance. Our code is available at https://github.com/cwb0611/Context-CAM.

Using docker to encapsulate the task has been regarded as a potential way to achieve efficient task orchestration and management in edge computing. Despite the lightweight nature of containers, downloading a larger container image can still be resource-intensive, particularly in resource-constrained edge environments. Fortunately, the unique layered architecture of the container allows multiple containerized tasks to share the same layer, thereby offering an opportunity for reducing the image downloading overhead via sharing the common layers. To explore the potential of layer sharing on image downloading over-head reduction, we investigate a joint task scheduling and image routing problem in edge environment, aiming at minimizing the image downloading overhead. We first formulate the problem into an integer linear programming form, and then propose a layer-aware scheduling and routing (LSR) algorithm to tackle this problem. Finally, to evaluate the effectiveness of our proposed algorithm, we conduct a group of simulation experiments. The experimental results show that our proposed algorithm can reduce the download time by about 20% in comparison with other approaches.

Salient object detection (SOD) has been attracting a lot of interest, and recently many computational models have been developed. Here, the authors formulate a SOD model, in which saliency map is computed as a combination of the colour, its distribution‐based saliency and orientation saliency. Similar to traditional SODs, the proposed method is based on super‐pixel segmentation and super‐pixel utilises both colour and its distribution‐based saliency to generate a coarse saliency map. However, distinct from traditional SODs, authors further use orientation contrast to optimise the coarse saliency map to obtain an improved saliency map. Authors’ contributions are twofold. First, the authors combine colour uniqueness and its distribution with local orientation information (LOI) used in Itti's model to effectively improve profiles of salient regions. Second, a reciprocal function is defined to substitute the Gabor function used in LOI, and the authors have proved that the substitution could detect relatively homogeneous and uniform regions at the boundary of salient object, whereas it is what the traditional models lack. Authors’ approach significantly outperforms state‐of‐the‐art methods on four benchmark datasets, while the authors demonstrate that the proposed method runs as fast as most existing algorithms.

In this paper, we consider a class of exponential sums from some half quadratic binomials. The exponential sums are proven to be eleven-valued with maximal magnitude (1/2(q - √q)) except for the trivial value q. As applications, first, we investigate the autocorrelation and cross-correlation distribution among the sequences in a sequence family. Second, we determine the weight distributions of several classes of linear codes. Some of the dual codes have minimum distance four, which are optimal with respect to the Hamming bound. Our results extend the result by Choi et al. and show that some correlation values in it do not occur.

In this paper, a class of exponential sum from some binomials is studied. As an application, we determine the weight distribution of a family of p-ary cyclic codes.

A new image retrieval method, which is based on composite of mean shift and assignment model and referred to CMSAM, is proposed. it matches each significant cluster of target image with one of retrieval image one by one and uses assignment model to seek a optimum cluster-pairs set between the two images. Based on the optimum cluster-pairs set, a similarity measure is defined. In comparison with most widely used methods based on color histogram, experimental results show that both recall and precision with CMSAM are improved significantly, in particular it can effectively retrieve such two images that their structures are similar but their colors are not identical, however, those methods canpsilat achieve such an retrieval result.

In this paper, a new image retrieval method, which uses the two primary features of image cluster to retrieve image, i.e., the average color value and the number of pixels for each cluster, is proposed. In comparison with popular methods, since this method uses both color feature and structure feature, it is good to solve such a sort of image retrieval questions for two images that they are similar but not identical color. Experimental results show that this method not only enhances the flexibility of system retrieval, but also achieves prominent effects for image retrieval.

An algorithm is developed to estimate visibility from images captured by video cameras. We propose to smooth the captured image by mean shift and extract the landmark edge by an improved ADM. Then the visibility is estimated in terms of a simplified visibility definition. In comparison with traditional methods, our method not only remove the noise in landmark boundary region, but also make boundary region be more uniform and the extracted edge be more salient. Experimental results illustrate the effectiveness of our approach in visibility estimation.