Search

As a bio-inspired vision sensor, the spike camera emulates the operational principles of the fovea, a compact retinal region, by employing spike discharges to encode the accumulation of per-pixel luminance intensity. Leveraging its high temporal resolution and bio-inspired neuromorphic design, the spike camera holds significant promise for advancing computer vision applications. Saliency detection mimics the behavior of human beings and captures the most salient region from the scenes. In this paper, we investigate the visual saliency in the continuous spike stream for the first time. To effectively process the binary spike stream, we propose a Recurrent Spiking Transformer (RST) framework, which is based on a full spiking neural network. Our framework enables the extraction of spatio-temporal features from the continuous spatio-temporal spike stream while maintaining low power consumption. To facilitate the training and validation of our proposed model, we build a comprehensive real-world spike-based visual saliency dataset, enriched with numerous light conditions. Extensive experiments demonstrate the superior performance of our Recurrent Spiking Transformer framework in comparison to other spike neural network-based methods. Our framework exhibits a substantial margin of improvement in capturing and highlighting visual saliency in the spike stream, which not only provides a new perspective for spike-based saliency segmentation but also shows a new paradigm for full SNN-based transformer models. The code and dataset are available at \url{https://github.com/BIT-Vision/SVS}., Comment: Accepted by AAAI 2024

The conductance of graphene nanoribbons and nanoconstrictions under the effect of a scanning gate microscopy tip is systematically studied. Using a scattering approach for noninvasive probes, the first- and second-order conductance corrections caused by the tip potential disturbance are expressed explicitly in terms of the scattering states of the unperturbed structure. Numerical calculations confirm the perturbative results, showing that the second-order term prevails in the conductance plateaus, exhibiting a universal scaling law for armchair graphene strips. For stronger tips, at specific probe potential widths and strengths beyond the perturbative regime, the conductance corrections reveal the appearance of resonances originated from states trapped below the tip. The zero-transverse-energy mode of an armchair metallic strip is shown to be insensitive to the long-range electrostatic potential of the probe. For nanoconstrictions defined on a strip, scanning gate microscopy allows to get insight into the breakdown of conductance quantization. The first-order correction generically dominates at low tip strength, while for Fermi energies associated with faint conductance plateaus, the second-order correction becomes dominant for relatively small potential tip strengths. In accordance with the spatial dependence of the partial local density of states, the largest tip effect occurs in the central part of the constriction, close to the edges. Nanoribbons and nanoconstrictions with zigzag edges exhibit a similar response as in the case of armchair nanostructures, except when the intervalley coupling induced by the tip potential destroys the chiral edge states., Comment: 21 pages, 16 figures

Federated Learning (FL) enables the multiple participating devices to collaboratively contribute to a global neural network model while keeping the training data locally. Unlike the centralized training setting, the non-IID, imbalanced (statistical heterogeneity) and distribution shifted training data of FL is distributed in the federated network, which will increase the divergences between the local models and the global model, further degrading performance. In this paper, we propose a flexible clustered federated learning (CFL) framework named FlexCFL, in which we 1) group the training of clients based on the similarities between the clients' optimization directions for lower training divergence; 2) implement an efficient newcomer device cold start mechanism for framework scalability and practicality; 3) flexibly migrate clients to meet the challenge of client-level data distribution shift. FlexCFL can achieve improvements by dividing joint optimization into groups of sub-optimization and can strike a balance between accuracy and communication efficiency in the distribution shift environment. The convergence and complexity are analyzed to demonstrate the efficiency of FlexCFL. We also evaluate FlexCFL on several open datasets and made comparisons with related CFL frameworks. The results show that FlexCFL can significantly improve absolute test accuracy by +10.6% on FEMNIST compared to FedAvg, +3.5% on FashionMNIST compared to FedProx, +8.4% on MNIST compared to FeSEM. The experiment results show that FlexCFL is also communication efficient in the distribution shift environment., Comment: Manuscript under review. arXiv admin note: substantial text overlap with arXiv:2010.06870

Federated learning (FL) is an emerging distributed machine learning paradigm that protects privacy and tackles the problem of isolated data islands. At present, there are two main communication strategies of FL: synchronous FL and asynchronous FL. The advantages of synchronous FL are that the model has high precision and fast convergence speed. However, this synchronous communication strategy has the risk that the central server waits too long for the devices, namely, the straggler effect which has a negative impact on some time-critical applications. Asynchronous FL has a natural advantage in mitigating the straggler effect, but there are threats of model quality degradation and server crash. Therefore, we combine the advantages of these two strategies to propose a clustered semi-asynchronous federated learning (CSAFL) framework. We evaluate CSAFL based on four imbalanced federated datasets in a non-IID setting and compare CSAFL to the baseline methods. The experimental results show that CSAFL significantly improves test accuracy by more than +5% on the four datasets compared to TA-FedAvg. In particular, CSAFL improves absolute test accuracy by +34.4% on non-IID FEMNIST compared to TA-FedAvg., Comment: This paper will be presented at IJCNN 2021

Federated Learning (FL) is a novel distributed machine learning which allows thousands of edge devices to train model locally without uploading data concentrically to the server. But since real federated settings are resource-constrained, FL is encountered with systems heterogeneity which causes a lot of stragglers directly and then leads to significantly accuracy reduction indirectly. To solve the problems caused by systems heterogeneity, we introduce a novel self-adaptive federated framework FedSAE which adjusts the training task of devices automatically and selects participants actively to alleviate the performance degradation. In this work, we 1) propose FedSAE which leverages the complete information of devices' historical training tasks to predict the affordable training workloads for each device. In this way, FedSAE can estimate the reliability of each device and self-adaptively adjust the amount of training load per client in each round. 2) combine our framework with Active Learning to self-adaptively select participants. Then the framework accelerates the convergence of the global model. In our framework, the server evaluates devices' value of training based on their training loss. Then the server selects those clients with bigger value for the global model to reduce communication overhead. The experimental result indicates that in a highly heterogeneous system, FedSAE converges faster than FedAvg, the vanilla FL framework. Furthermore, FedSAE outperforms than FedAvg on several federated datasets - FedSAE improves test accuracy by 26.7% and reduces stragglers by 90.3% on average., Comment: This paper will be presented at IJCNN 2021

Federated Learning (FL) enables the multiple participating devices to collaboratively contribute to a global neural network model while keeping the training data locally. Unlike the centralized training setting, the non-IID and imbalanced (statistical heterogeneity) training data of FL is distributed in the federated network, which will increase the divergences between the local models and global model, further degrading performance. In this paper, we propose a novel clustered federated learning (CFL) framework FedGroup, in which we 1) group the training of clients based on the similarities between the clients' optimization directions for high training performance; 2) construct a new data-driven distance measure to improve the efficiency of the client clustering procedure. 3) implement a newcomer device cold start mechanism based on the auxiliary global model for framework scalability and practicality. FedGroup can achieve improvements by dividing joint optimization into groups of sub-optimization and can be combined with FL optimizer FedProx. The convergence and complexity are analyzed to demonstrate the efficiency of our proposed framework. We also evaluate FedGroup and FedGrouProx (combined with FedProx) on several open datasets and made comparisons with related CFL frameworks. The results show that FedGroup can significantly improve absolute test accuracy by +14.1% on FEMNIST compared to FedAvg. +3.4% on Sentiment140 compared to FedProx, +6.9% on MNIST compared to FeSEM., Comment: This work will be presented at IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA) 2021. NOTE: This revision contains a crucial correction of the client cold start mechanism, please discard all previous manuscripts

Federated learning (FL) is a distributed deep learning method which enables multiple participants, such as mobile phones and IoT devices, to contribute a neural network model while their private training data remains in local devices. This distributed approach is promising in the edge computing system where have a large corpus of decentralized data and require high privacy. However, unlike the common training dataset, the data distribution of the edge computing system is imbalanced which will introduce biases in the model training and cause a decrease in accuracy of federated learning applications. In this paper, we demonstrate that the imbalanced distributed training data will cause accuracy degradation in FL. To counter this problem, we build a self-balancing federated learning framework call Astraea, which alleviates the imbalances by 1) Global data distribution based data augmentation, and 2) Mediator based multi-client rescheduling. The proposed framework relieves global imbalance by runtime data augmentation, and for averaging the local imbalance, it creates the mediator to reschedule the training of clients based on Kullback-Leibler divergence (KLD) of their data distribution. Compared with FedAvg, the state-of-the-art FL algorithm, Astraea shows +5.59% and +5.89% improvement of top-1 accuracy on the imbalanced EMNIST and imbalanced CINIC-10 datasets, respectively. Meanwhile, the communication traffic of Astraea can be 82% lower than that of FedAvg., Comment: Published as a conference paper at IEEE 37th International Conference on Computer Design (ICCD) 2019

We study a relativistic quantum cavity system realized by etching out from a graphene sheet by quantum transport measurements and theoretical calculations. The conductance of the graphene cavity has been measured as a function of the back gate voltage (or the Fermi energy) and the magnetic field applied perpendicular to the graphene sheet, and characteristic conductance contour patterns are observed in the measurements. In particular, two types of high conductance contour lines, i.e., straight and parabolic-like high conductance contour lines, are found in the measurements. The theoretical calculations are performed within the framework of tight-binding approach and Green's function formalism. Similar characteristic high conductance contour features as in the experiments are found in the calculations. The wave functions calculated at points selected along a straight conductance contour line are found to be dominated by a chain of scars of high probability distributions arranged as a necklace following the shape of cavity and the current density distributions calculated at these point are dominated by an overall vortex in the cavity. These characteristics are found to be insensitive to increasing magnetic field. However, the wave function probability distributions and the current density distributions calculated at points selected along a parabolic-like contour line show a clear dependence on increasing magnetic field, and the current density distributions at these points are characterized by the complex formation of several localized vortices in the cavity. Our work brings a new insight into quantum chaos in relativistic particle systems and would greatly stimulate experimental and theoretical efforts towards this still emerging field., Comment: 20 pages, 6 figures