Energy-Efficient Spiking Segmenter for Frame and Event-Based Images.

Semantic segmentation predicts dense pixel-wise semantic labels, which is crucial for autonomous environment perception systems. For applications on mobile devices, current research focuses on energy-efficient segmenters for both frame and event-based cameras. However, there is currently no artificial neural network (ANN) that can perform efficient segmentation on both types of images. This paper introduces spiking neural network (SNN, a bionic model that is energy-efficient when implemented on neuromorphic hardware) and develops a Spiking Context Guided Network (Spiking CGNet) with substantially lower energy consumption and comparable performance for both frame and event-based images. First, this paper proposes a spiking context guided block that can extract local features and context information with spike computations. On this basis, the directly-trained SCGNet-S and SCGNet-L are established for both frame and event-based images. Our method is verified on the frame-based dataset Cityscapes and the event-based dataset DDD17. On the Cityscapes dataset, SCGNet-S achieves comparable results to ANN CGNet with 4.85 × energy efficiency. On the DDD17 dataset, Spiking CGNet outperforms other spiking segmenters by a large margin.

IDSNN: Towards High-Performance and Low-Latency SNN Training via Initialization and Distillation.

Spiking neural networks (SNNs) are widely recognized for their biomimetic and efficient computing features. They utilize spikes to encode and transmit information. Despite the many advantages of SNNs, they suffer from the problems of low accuracy and large inference latency, which are, respectively, caused by the direct training and conversion from artificial neural network (ANN) training methods. Aiming to address these limitations, we propose a novel training pipeline (called IDSNN) based on parameter initialization and knowledge distillation, using ANN as a parameter source and teacher. IDSNN maximizes the knowledge extracted from ANNs and achieves competitive top-1 accuracy for CIFAR10 (94.22%) and CIFAR100 (75.41%) with low latency. More importantly, it can achieve 14× faster convergence speed than directly training SNNs under limited training resources, which demonstrates its practical value in applications.

Direct training high-performance spiking neural networks for object recognition and detection.

Introduction: The spiking neural network (SNN) is a bionic model that is energy-efficient when implemented on neuromorphic hardwares. The non-differentiability of the spiking signals and the complicated neural dynamics make direct training of high-performance SNNs a great challenge. There are numerous crucial issues to explore for the deployment of direct training SNNs, such as gradient vanishing and explosion, spiking signal decoding, and applications in upstream tasks. Methods: To address gradient vanishing, we introduce a binary selection gate into the basic residual block and propose spiking gate (SG) ResNet to implement residual learning in SNNs. We propose two appropriate representations of the gate signal and verify that SG ResNet can overcome gradient vanishing or explosion by analyzing the gradient backpropagation. For the spiking signal decoding, a better decoding scheme than rate coding is achieved by our attention spike decoder (ASD), which dynamically assigns weights to spiking signals along the temporal, channel, and spatial dimensions. Results and discussion: The SG ResNet and ASD modules are evaluated on multiple object recognition datasets, including the static ImageNet, CIFAR-100, CIFAR-10, and neuromorphic DVS-CIFAR10 datasets. Superior accuracy is demonstrated with a tiny simulation time step of four, specifically 94.52% top-1 accuracy on CIFAR-10 and 75.64% top-1 accuracy on CIFAR-100. Spiking RetinaNet is proposed using SG ResNet as the backbone and ASD module for information decoding as the first direct-training hybrid SNN-ANN detector for RGB images. Spiking RetinaNet with a SG ResNet34 backbone achieves an mAP of 0.296 on the object detection dataset MSCOCO.

Stable Isotopes Reveal Photoreduction of Particle-Bound Mercury Driven by Water-Soluble Organic Carbon during Severe Haze.

Haze with high loading of particles may result in significant enrichment of particle-bound Hg (PBM), potentially impacting the atmospheric Hg transformation and transport. However, the dynamics of Hg transformation and the relative environmental effect during severe haze episodes remain unclear. Here, we report Hg isotopic compositions of atmospheric particles (PM2.5, PM10, and TSP) collected during a severe haze episode in Tianjin, China, to investigate the transformation and fate of Hg during haze events. All severe haze samples display significantly higher Δ199Hg (up to 1.50‰) than global urban PBM, which cannot be explained by primary anthropogenic emissions. The high Δ199Hg is likely caused by photoreduction of PBM promoted by water-soluble organic carbon (WSOC) during the particle accumulation period, as demonstrated by the positive correlations of Δ199Hg with WSOC and relative humidity and confirmed by our laboratory-controlled photoreduction experiment. The results show that, on average, 21% of PBM are likely photoreduced and re-emitted back to the atmosphere as Hg(0), potentially requiring revision of atmospheric Hg budgeting and modeling. This study highlights the release of large portions of PBM back to the gas phase through photoreduction, which needs to be taken into account while evaluating the atmospheric Hg cycle and the relative ecological effects.