Despite the progress made by few-shot segmentation (FSS) in low-data regimes, the generalization capability of most previous works could be fragile when countering hard query samples with seen-class objects. This paper proposes a fresh and powerful scheme to tackle such an intractable bias problem, dubbed base and meta (BAM). Concretely, we apply an auxiliary branch (base learner) to the conventional FSS framework (meta learner) to explicitly identify base-class objects, i.e., the regions that do not need to be segmented. Then, the coarse results output by these two learners in parallel are adaptively integrated to derive accurate segmentation predictions. Considering the sensitivity of meta learner, we further introduce adjustment factors to estimate the scene differences between support and query image pairs from both style and appearance perspectives, so as to facilitate the model ensemble forecasting. The remarkable performance gains on standard benchmarks (PASCAL-5 $^{i}$ , COCO-20 $^{i}$ , and FSS-1000) manifest the effectiveness, and surprisingly, our versatile scheme sets new state-of-the-arts even with two plain learners. Furthermore, in light of its unique nature, we also discuss several more practical but challenging extensions, including generalized FSS, 3D point cloud FSS, class-agnostic FSS, cross-domain FSS, weak-label FSS, and zero-shot segmentation. Our source code is available at https://github.com/chunbolang/BAM .

Edge computing has become increasingly important to fulfill the diversified Quality-of-Service (QoS) or Quality-of-Experience (QoE) demands for Industrial Internet of Things (IIoT) applications, such as machine condition monitoring, fault diagnosis, intelligent production scheduling, and production quality control. Due to the heterogeneity of IIoT systems, it is of urgent necessity to concentrate on the cloud–edge–end cooperative partial task offloading and resource allocation (CPTORA) problem for realizing workload balancing, efficient resource utilization, and better QoS/QoE of IIoT applications. However, the challenge lies in how to make real-time, accurate, decentralized task offloading (TO) and resource allocation (RA) decisions for dynamic and device-intensive IIoT. Therefore, this work examines the CPTORA problem for IIoT, aiming at minimizing its long-run overall delay and energy costs. To lower the problem complexity, this problem is decomposed into the TO subproblem and the RA subproblem. Then, an improved soft actor–critic-based decentralized multiagent deep reinforcement learning (MADRL) algorithm is proposed to address the TO subproblem, where each IIoT device can learn its globally optimal policy and make its decisions independently. This algorithm innovatively combines the divergence regularization, the distributional reinforcement learning, and the value function decomposition methods to improve convergence speed and accuracy of the existing MADRL methods. After receiving the TO decisions of every IIoT device, every edge server employs the Lagrange multiplier method and Karush–Kuhn–Tucker condition to solve its RA subproblem. The experimental results show that the proposed algorithm decreases the overall delay and energy costs more effectively, compared to the other state-of-the-art MADRL approaches.

Unlike radio communication in terrestrial wireless sensor networks, acoustic channel in underwater wireless sensor network (UWSN) is challenged by long propagation delay and swarm mobility. The long propagation delay causes the deterioration of network throughput and unfairness. Moreover, the swarm mobility causes unreliable access and the failure of channel reservation. In this paper, we propose a novel delay tolerant MAC protocol (DTMAC) inspired by the coupon collector's problem. It proposes a distributed coupon collection algorithm in UWSNs. If a node needs to send a packet, the packet will be repeatedly transmitted $m$ times, with a transmission probability to be $p$ . Under the traditional protocol interference model, we first set up a probability model for throughput of DTMAC, and then give the throughput-optimal value for $m$ and $p$ with the successful transmission probability as tuning parameter. Because no any acknowledge or channel reservation is used, the throughput of DTMAC is not influenced by propagation delay. In addition, space unfairness problem also no longer exists since DTMAC is not concerned with transmission distance. The simulation results show that the throughput of DTMAC greatly outperforms that of MAC protocol with RTS/CTS scheme in most underwater scenarios.

Benefiting from advances in few-shot learning techniques, their application to dense prediction tasks ( e.g ., segmentation) has also made great strides in the past few years. However, most existing few-shot segmentation (FSS) approaches follow a similar pipeline to that of few-shot classification, where some core components are directly exploited regardless of various properties between tasks. We note that such an ill-conceived framework introduces unnecessary information loss, which is clearly unacceptable given the already very limited training sample. To this end, we delve into the typical types of information loss and provide a reasonably effective way, namely Retain And REcover (RARE). The main focus of this paper can be summarized as follows: (i) the loss of spatial information due to global pooling; (ii) the loss of boundary information due to mask interpolation; (iii) the degradation of representational power due to sample averaging. Accordingly, we propose a series of strategies to retain/recover the avoidable/unavoidable information, such as unidirectional pooling, error-prone region focusing, and adaptive integration. Extensive experiments on two popular benchmarks ( i.e ., PASCAL-5 ⁱ and COCO-20 ⁱ ) demonstrate the effectiveness of our scheme, which is not restricted to a particular baseline approach. The ultimate goal of our work is to address different information loss problems within a unified framework, and it also exhibits superior performance compared to other methods with similar motivations. The source code will be made available at https://github.com/chunbolang/RARE.

Physical adversarial attacks against deep neural networks (DNNs) have recently gained increasing attention. The current mainstream physical attacks use printed adversarial patches or camouflage to alter the appearance of the target object. However, these approaches generate conspicuous adversarial patterns that show poor stealthiness. Another physical deployable attack is the optical attack, featuring stealthiness while exhibiting weakly in the daytime with sunlight. In this paper, we propose a novel Reflected Light Attack (RFLA), featuring effective and stealthy in both the digital and physical world, which is implemented by placing the color transparent plastic sheet and a paper cut of a specific shape in front of the mirror to create different colored geometries on the target object. To achieve these goals, we devise a general framework based on the circle to model the reflected light on the target object. Specifically, we optimize a circle (composed of a coordinate and radius) to carry various geometrical shapes determined by the optimized angle. The fill color of the geometry shape and its corresponding transparency are also optimized. We extensively evaluate the effectiveness of RFLA on different datasets and models. Experiment results suggest that the proposed method achieves over 99% success rate on different datasets and models in the digital world. Additionally, we verify the effectiveness of the proposed method in different physical environments by using sunlight or a flashlight.