SpikeSMOKE: Spiking Neural Networks for Monocular 3D Object Detection with Cross-Scale Gated Coding

• URL: http://arxiv.org/abs/2506.07737v2
• Date: Wed, 11 Jun 2025 15:55:43 GMT
• Title: SpikeSMOKE: Spiking Neural Networks for Monocular 3D Object Detection with Cross-Scale Gated Coding
• Authors: Xuemei Chen, Huamin Wang, Hangchi Shen, Shukai Duan, Shiping Wen, Tingwen Huang,
• Abstract summary: SpikeSMOKE is a new attempt for low-power monocular 3D object detection.<n>SpikeSMOKE can significantly reduce energy consumption compared to the results on SMOKE.
• Score: 40.87826765639894
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Low energy consumption for 3D object detection is an important research area because of the increasing energy consumption with their wide application in fields such as autonomous driving. The spiking neural networks (SNNs) with low-power consumption characteristics can provide a novel solution for this research. Therefore, we apply SNNs to monocular 3D object detection and propose the SpikeSMOKE architecture in this paper, which is a new attempt for low-power monocular 3D object detection. As we all know, discrete signals of SNNs will generate information loss and limit their feature expression ability compared with the artificial neural networks (ANNs).In order to address this issue, inspired by the filtering mechanism of biological neuronal synapses, we propose a cross-scale gated coding mechanism(CSGC), which can enhance feature representation by combining cross-scale fusion of attentional methods and gated filtering mechanisms.In addition, to reduce the computation and increase the speed of training, we present a novel light-weight residual block that can maintain spiking computing paradigm and the highest possible detection performance. Compared to the baseline SpikeSMOKE under the 3D Object Detection, the proposed SpikeSMOKE with CSGC can achieve 11.78 (+2.82, Easy), 10.69 (+3.2, Moderate), and 10.48 (+3.17, Hard) on the KITTI autonomous driving dataset by AP|R11 at 0.7 IoU threshold, respectively. It is important to note that the results of SpikeSMOKE can significantly reduce energy consumption compared to the results on SMOKE. For example,the energy consumption can be reduced by 72.2% on the hard category, while the detection performance is reduced by only 4%. SpikeSMOKE-L (lightweight) can further reduce the amount of parameters by 3 times and computation by 10 times compared to SMOKE.

Related papers

• Spiking Meets Attention: Efficient Remote Sensing Image Super-Resolution with Attention Spiking Neural Networks [57.17129753411926]
  Spiking neural networks (SNNs) are emerging as a promising alternative to traditional artificial neural networks (ANNs)<n>We propose SpikeSR, which achieves state-of-the-art performance across various remote sensing benchmarks such as AID, DOTA, and DIOR.
  arXiv  Detail & Related papers  (2025-03-06T09:06:06Z)
• SpikeDet: Better Firing Patterns for Accurate and Energy-Efficient Object Detection with Spiking Neuron Networks [13.848361661516595]
  Spiking Neural Networks (SNNs) are the third generation of neural networks.<n>They have gained widespread attention in object detection due to their low power consumption and biological interpretability.<n>Existing SNN-based object detection methods suffer from local firing saturation, where neurons in information-concentrated regions fire continuously throughout all time steps.<n>This abnormal neuron firing pattern reduces the feature discrimination capability and detection accuracy, while also increasing the firing rates that prevent SNNs from achieving their potential energy efficiency.
  arXiv  Detail & Related papers  (2025-01-25T09:24:14Z)
• DM3D: Distortion-Minimized Weight Pruning for Lossless 3D Object Detection [42.07920565812081]
  We propose a novel post-training weight pruning scheme for 3D object detection. It determines redundant parameters in the pretrained model that lead to minimal distortion in both locality and confidence. This framework aims to minimize detection distortion of network output to maximally maintain detection precision.
  arXiv  Detail & Related papers  (2024-07-02T09:33:32Z)
• Low-power event-based face detection with asynchronous neuromorphic hardware [2.0774873363739985]
  We present the first instance of an on-chip spiking neural network for event-based face detection deployed on the SynSense Speck neuromorphic chip. We show how to reduce precision discrepancies between off-chip clock-driven simulation used for training and on-chip event-driven inference. We achieve an on-chip face detection mAP[0.5] of 0.6 while consuming only 20 mW.
  arXiv  Detail & Related papers  (2023-12-21T19:23:02Z)
• Enabling energy-Efficient object detection with surrogate gradient descent in spiking neural networks [0.40054215937601956]
  Spiking Neural Networks (SNNs) are a biologically plausible neural network model with significant advantages in both event-driven processing and processing-temporal information. In this study, we introduce the Current Mean Decoding (CMD) method, which solves the regression problem to facilitate the training of deep SNNs for object detection tasks. Based on the gradient surrogate and CMD, we propose the SNN-YOLOv3 model for object detection.
  arXiv  Detail & Related papers  (2023-09-07T15:48:00Z)
• Pushing the Limits of Asynchronous Graph-based Object Detection with Event Cameras [62.70541164894224]
  We introduce several architecture choices which allow us to scale the depth and complexity of such models while maintaining low computation. Our method runs 3.7 times faster than a dense graph neural network, taking only 8.4 ms per forward pass.
  arXiv  Detail & Related papers  (2022-11-22T15:14:20Z)
• Sparse Compressed Spiking Neural Network Accelerator for Object Detection [0.1246030133914898]
  Spiking neural networks (SNNs) are inspired by the human brain and transmit binary spikes and highly sparse activation maps. This paper proposes a sparse compressed spiking neural network accelerator that takes advantage of the high sparsity of activation maps and weights. The experimental result of the neural network shows 71.5$%$ mAP with mixed (1,3) time steps on the IVS 3cls dataset.
  arXiv  Detail & Related papers  (2022-05-02T09:56:55Z)
• An Empirical Study of Adder Neural Networks for Object Detection [67.64041181937624]
  Adder neural networks (AdderNets) have shown impressive performance on image classification with only addition operations. We present an empirical study of AdderNets for object detection.
  arXiv  Detail & Related papers  (2021-12-27T11:03:13Z)
• SpikeDyn: A Framework for Energy-Efficient Spiking Neural Networks with Continual and Unsupervised Learning Capabilities in Dynamic Environments [14.727296040550392]
  Spiking Neural Networks (SNNs) bear the potential of efficient unsupervised and continual learning capabilities because of their biological plausibility. We propose SpikeDyn, a framework for energy-efficient SNNs with continual and unsupervised learning capabilities in dynamic environments.
  arXiv  Detail & Related papers  (2021-02-28T08:26:23Z)
• Reinforced Axial Refinement Network for Monocular 3D Object Detection [160.34246529816085]
  Monocular 3D object detection aims to extract the 3D position and properties of objects from a 2D input image. Conventional approaches sample 3D bounding boxes from the space and infer the relationship between the target object and each of them, however, the probability of effective samples is relatively small in the 3D space. We propose to start with an initial prediction and refine it gradually towards the ground truth, with only one 3d parameter changed in each step. This requires designing a policy which gets a reward after several steps, and thus we adopt reinforcement learning to optimize it.
  arXiv  Detail & Related papers  (2020-08-31T17:10:48Z)
• Adaptive Anomaly Detection for IoT Data in Hierarchical Edge Computing [71.86955275376604]
  We propose an adaptive anomaly detection approach for hierarchical edge computing (HEC) systems to solve this problem. We design an adaptive scheme to select one of the models based on the contextual information extracted from input data, to perform anomaly detection. We evaluate our proposed approach using a real IoT dataset, and demonstrate that it reduces detection delay by 84% while maintaining almost the same accuracy as compared to offloading detection tasks to the cloud.
  arXiv  Detail & Related papers  (2020-01-10T05:29:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.