Weakly supervised object detection (WSOD) has attracted significant attention in recent years, as it does not require box-level annotations. State-of-the-art methods generally adopt a multi-module network, which employs WSDDN as the multiple instance detection network module and uses multiple instance refinement modules to refine performance. However, these approaches suffer from three key limitations. First, existing methods tend to generate pseudo GT boxes that either focus only on discriminative parts, failing to capture the whole object, or cover the entire object but fail to distinguish between adjacent intra-class instances. Second, the foundational WSDDN architecture lacks a crucial background class representation for each proposal and exhibits a large semantic gap between its branches. Third, prior methods discard ignored proposals during optimization, leading to slow convergence. To address these challenges, we propose the Dual-thresholded heAtmap-guided proposal clustering and Negative Certainty supervision with Enhanced base network (DANCE) method for WSOD. Specifically, we first devise a heatmap-guided proposal selector (HGPS) algorithm, which utilizes dual thresholds on heatmaps to pre-select proposals, enabling pseudo GT boxes to both capture the full object extent and distinguish between adjacent intra-class instances. We then construct a weakly supervised basic detection network (WSBDN), which augments each proposal with a background class representation and uses heatmaps for pre-supervision to bridge the semantic gap between matrices. At last, we introduce a negative certainty supervision (NCS) loss on ignored proposals to accelerate convergence. Extensive experiments on the challenging PASCAL VOC and MS COCO datasets demonstrate the effectiveness and superiority of our method. Our code is publicly available at https://github.com/gyl2565309278/DANCE.

Machine learning models are vulnerable to membership inference attacks (MIAs), where adversaries attempt to predict whether specific samples are part of the model’s training set. Previous studies have demonstrated a strong correlation between the distinguishability of training and testing loss distributions and the model’s susceptibility to MIAs. Motivated by existing results, we propose a novel training framework called LossControl, which focuses on manipulating loss to mitigate privacy leaks. In LossControl, we first utilize Soft-label Training to replace the general learning process, which facilitates model training while improving generalization. Next, we monitor overfitting samples during the training process and prevent further loss reduction by applying our designed Loss Ascent to these samples without sacrificing model performance. Through extensive evaluations across four diverse datasets (including images, medical data, and transaction records), our method consistently outperforms defense mechanisms against state-of-the-art attacks and achieves optimal model performance in most experiments, demonstrating LossControl’s superior resilience against MIAs and its ability to strike an unparalleled balance between privacy and utility.

Recent advancements in deep neural networks have significantly enhanced the performance of semantic segmentation. However, class imbalance and instance imbalance remain persistent challenges, where smaller instances and thin boundaries are often overshadowed by larger structures. To address the multiscale nature of segmented objects, various models have incorporated mechanisms such as spatial attention and feature pyramid networks. Despite these advancements, most loss functions are still primarily pixel-wise, while regional and boundary-focused loss functions often incur high computational costs or are restricted to small-scale regions. To address this limitation, we propose the complex wavelet mutual information (CWMI) loss, a novel loss function that leverages mutual information from subband images decomposed by a complex steerable pyramid. The complex steerable pyramid captures features across multiple orientations and preserves structural similarity across scales. Meanwhile, mutual information is well-suited to capturing high-dimensional directional features and offers greater noise robustness. Extensive experiments on diverse segmentation datasets demonstrate that CWMI loss achieves significant improvements in both pixel-wise accuracy and topological metrics compared to state-of-the-art methods, while introducing minimal computational overhead. Our code is available at https://github.com/lurenhaothu/CWMI

Offline goal-conditioned reinforcement learning (GCRL) aims at solving goal-reaching tasks with sparse rewards from an offline dataset. While prior work has demonstrated various approaches for agents to learn near-optimal policies, these methods encounter limitations when dealing with diverse constraints in complex environments, such as safety constraints. Some of these approaches prioritize goal attainment without considering safety, while others excessively focus on safety at the expense of training efficiency. In this paper, we study the problem of constrained offline GCRL and propose a new method called Recovery-based Supervised Learning (RbSL) to accomplish safety-critical tasks with various goals. To evaluate the method performance, we build a benchmark based on the robot-fetching environment with a randomly positioned obstacle and use expert or random policies to generate an offline dataset. We compare RbSL with three offline GCRL algorithms and one offline safe RL algorithm. As a result, our method outperforms the existing state-of-the-art methods to a large extent. Furthermore, we validate the practicality and effectiveness of RbSL by deploying it on a real Panda manipulator. Code is available at https://github.com/Sunlighted/RbSL.git.

Utilizing the federated learning (FL) technique, data owners can collaboratively train artificial intelligence models, retaining all training data on their premises to minimize the potential for personal data breaches. However, self-interested users (e.g., free riders) bring new challenges that hinder the development of FL techniques. To this end, we propose a two-stage client selection scheme comprising a multiarmed bandit (MAB)-based candidate client selection method and an auction-based training client selection method. Specifically, our client selection scheme initially formulates the FL system into an MAB system, where clients are the arms and the server is the player. Then, we quantify the similarity between a local model and the server side, which is the designed metric for model aggregation and reward computation updating based on the fuzzy mathematical strategy. Next, based on the Thompson Sampling strategy, the server can intelligently determine the reward of each client, and clients with more significant rewards have the chance for local model training. With an auction method, the server can determine the training clients to reduce the training cost while maximizing each client’s revenue. Extensive experiments on real-world data sets demonstrate that the proposed scheme outperforms representative FL schemes (i.e., FedAvg, FedProx, FedMax, and MFL) regarding the model’s convergence rate and cost in FL systems with free riders.

Federated Learning empowers data owners to collectively train an artificial intelligence model without exposing data. However, the heterogeneous resources and the self-interested users bring new challenges hindering the development of federated learning. To this end, we propose a Multi-attribute Auction-based Grouped Federated Learning scheme, called MAGFL, comprising a grouped federated learning framework and a multi-attribute auction-based group selection strategy. Initially, our grouped federated learning framework clusters clients into groups according to local characteristics. Then, we propose a quality assessment method to assess the quality of each group based on a fuzzy approach. Furthermore, the FL server distributes economic rewards to training clients to motivate more clients to join the FL system, which is likened to a multi-attribute auction market where each group agent bids for training opportunities. Moreover, we design a novel global model update method with added Adam (i.e., Adaptive Moment Estimation) operations into the global update stage, which can fully utilize the local and global update direction to accelerate the convergence rate of scheme MGAFL. Extensive experiments on real-world datasets demonstrate that the proposed scheme outperforms representative federated learning schemes (i.e., FedAvg, FedProx, and FedAvg-Adam) regarding the model's convergence rate and capacity to deal with heterogeneous systems.

Federated Learning (FL), allowing data owners to conduct model training without sending their raw data to third-party servers, can enhance data privacy in Mobile Edge Computing (MEC) which brings data processing closer to the data sources. However, the heterogeneity of local data and constrained local resources in MEC bring new challenges hindering the development of FL. To this end, we propose an Auction-based Cluster Federated Learning scheme, called ACFL, comprising a clustered FL framework and an auction-based client selection strategy. Our clustered FL framework first introduces a mean-shift clustering algorithm to FL, which can intelligently cluster clients according to their local data distribution. Then, we select clients from each cluster using an auction mechanism to participate in FL training, which can mitigate the impact of data heterogeneity on model convergence and balance energy consumption. Moreover, we prove the proposed clustered FL framework converges at a sublinear rate. Extensive experiments conducted on real-world datasets demonstrate that the proposed FL scheme outperforms the conventional FL schemes in terms of convergence rate and energy balance.

Recently, the increase of different services makes the design of routing protocols more difficult in mobile ad hoc networks (MANETs), e.g., how to guarantee the QoS of different types of traffics flows in MANETs with resource constrained and malicious nodes. opportunistic routing (OR) can make full use of the broadcast characteristics of wireless channels to improve the performance of MANETs. In this paper, we propose a traffic-differentiated secure opportunistic routing from a game theoretic perspective, DSOR. In the proposed scheme, we use a novel method to calculate trust value, considering node's forwarding capability and the status of different types of flows. According to the resource status of the network, we propose a service price and resource price for the auction model, which is used to select optimal candidate forwarding sets. At the same time, the optimal bid price has been proved and a novel flow priority decision for transmission is presented, which is based on waiting time and requested time. The simulation results show that the network lifetime, packet delivery rate and delay of the DSOR are better than existing works.

In recent years, the Social Internet of Things (SIoT) has become a research hot topic in the field of wireless networks, which are inseparable relationships between human and devices. As a huge numbers of heterogeneous devices will be connected, it needs more frequency spectrum. The Cognitive radio (CR) technology can improve spectrum utilization in an opportunistic communication manner. However, dynamic spectrum availability and heterogeneous devices make it more difficult for routing design in CR-SIoT. Opportunistic routing (OR) can mitigate drawbacks from CR-SIoT, which leverages the broadcast nature of wireless channels. In this work, we propose an energy and trust aware OR in CR-SIoT, which jointly considers energy efferent, trust and social feature for designing secure OR. In the proposed scheme, we exploit a new routing metric for selecting forwarding candidates and use network coding for the data transmission between trust nodes in multiple types of flows SIoT. In addition, we propose a game-theoretic approach to allocate channel for SIoT which is based on interference factor. Extensive simulation results show that the proposed secure opportunistic routing performs better compared with existing routing in SIoT in terms of packet delivery ratio, network lifetime and average delay. To the best of our knowledge, the proposed routing scheme is the first OR in SIoT.