Accurate and Efficient LIF-Nets for 3D Detection and Recognition

Shi, Yueting; Li, Hai; Zhang, Hehui; Wu, Zhenzhi; Ren, Shiwei

doi:10.1109/access.2020.2995886

Cited by 8 publications

(3 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, compared with Conv3D and ConvLSTM, ConvLIAF can save a significant amount of computational resources and storage overhead. The impact on accuracy is reported in literature Shi et al ( 2020 ) and Wu et al ( 2021 ), and is also discussed in our experiment section.…”

Section: Generalized Spatiotemporal Processing Via Neural Dynamicssupporting

confidence: 69%

BIDL: a brain-inspired deep learning framework for spatiotemporal processing

Wu¹,

Shen²,

Zhang³

et al. 2023

Front. Neurosci.

Self Cite

View full text Add to dashboard Cite

Brain-inspired deep spiking neural network (DSNN) which emulates the function of the biological brain provides an effective approach for event-stream spatiotemporal perception (STP), especially for dynamic vision sensor (DVS) signals. However, there is a lack of generalized learning frameworks that can handle various spatiotemporal modalities beyond event-stream, such as video clips and 3D imaging data. To provide a unified design flow for generalized spatiotemporal processing (STP) and to investigate the capability of lightweight STP processing via brain-inspired neural dynamics, this study introduces a training platform called brain-inspired deep learning (BIDL). This framework constructs deep neural networks, which leverage neural dynamics for processing temporal information and ensures high-accuracy spatial processing via artificial neural network layers. We conducted experiments involving various types of data, including video information processing, DVS information processing, 3D medical imaging classification, and natural language processing. These experiments demonstrate the efficiency of the proposed method. Moreover, as a research framework for researchers in the fields of neuroscience and machine learning, BIDL facilitates the exploration of different neural models and enables global-local co-learning. For easily fitting to neuromorphic chips and GPUs, the framework incorporates several optimizations, including iteration representation, state-aware computational graph, and built-in neural functions. This study presents a user-friendly and efficient DSNN builder for lightweight STP applications and has the potential to drive future advancements in bio-inspired research.

show abstract

Section: Generalized Spatiotemporal Processing Via Neural Dynamicssupporting

confidence: 69%

BIDL: a brain-inspired deep learning framework for spatiotemporal processing

Wu¹,

Shen²,

Zhang³

et al. 2023

Front. Neurosci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this paper, we feed the static image a (l=0) ∈ R d0 to our input layer and convert it to the binary map s (1) = H(u (1) − u th ), where u (1) = W (1) a (0) . In the context of SNNs, this direct image input is called direct encoding (Shi et al, 2020;Rueckauer et al, 2017;Zheng et al, 2021;Rathi & Roy, 2020;Lu & Sengupta, 2020). The difference to the SNN's direct encoding is that our encoding outputs the binary map, not the spike train.…”

Section: Encodingmentioning

confidence: 99%

S$^3$NN: Time Step Reduction of Spiking Surrogate Gradients for Training Energy Efficient Single-Step Spiking Neural Networks

Suetake¹,

Ikegawa²,

Saiin³

et al. 2022

Preprint

View full text Add to dashboard Cite

As the scales of neural networks increase, techniques that enable them to run with low computational cost and energy efficiency are required. From such demands, various efficient neural network paradigms, such as spiking neural networks (SNNs) or binary neural networks (BNNs), have been proposed. However, they have sticky drawbacks, such as degraded inference accuracy and latency. To solve these problems, we propose a singlestep neural network (S 2 NN), an energy-efficient neural network with low computational cost and high precision. The proposed S 2 NN processes the information between hidden layers by spikes as SNNs. Nevertheless, it has no temporal dimension so that there is no latency within training and inference phases as BNNs. Thus, the proposed S 2 NN has a lower computational cost than SNNs that require time-series processing. However, S 2 NN cannot adopt naïve backpropagation algorithms due to the non-differentiability nature of spikes. We deduce a suitable neuron model by reducing the surrogate gradient for multi-time step SNNs to a single-time step. We experimentally demonstrated that the obtained neuron model enables S 2 NN to train more accurately and energy-efficiently than existing neuron models for SNNs and BNNs. We also showed that the proposed S 2 NN could achieve comparable accuracy to full-precision networks while being highly energy-efficient.

show abstract

“…Li et al [12] proposed 3D compression with excitation encoder-decoder structure and adopted focal loss as the loss function to solve the imbalance of positive and negative samples. Shi et al [13] proposed a brain-inspired LIF-NET using the spatiotemporal properties of the novel LIF neural network and achieved comparable detection accuracy while reducing computation complexity by over 60%. While the one-stage lung nodule detection methods described above are fast and consume fewer resources, they usually have a higher false-positive rate.…”

Section: Introductionmentioning

confidence: 99%

Channel-Wise Attention Mechanism in the 3D Convolutional Network for Lung Nodule Detection

et al. 2022

Self Cite

View full text Add to dashboard Cite

Pulmonary nodule detection is essential to reduce the mortality of lung cancer. One-stage detection methods have recently emerged as high-performance and lower-power alternatives to two-stage lung nodule detection methods. However, it is difficult for existing one-stage detection networks to balance sensitivity and specificity. In this paper, we propose an end-to-end detection mechanism combined with a channel-wise attention mechanism based on a 3D U-shaped residual network. First, an improved attention gate (AG) is introduced to reduce the false positive rate by employing critical feature dimensions at skip connections for feature propagation. Second, a channel interaction unit (CIU) is designed before the detection head to further improve detection sensitivity. Furthermore, the gradient harmonizing mechanism (GHM) loss function is adopted to solve the problem caused by the imbalance of positive and negative samples. We conducted experiments on the LUNA16 dataset and achieved a performance with a competition performance metric (CPM) score of 89.5% and sensitivity of 95%. The proposed method outperforms existing models in terms of sensitivity and specificity while maintaining the attractiveness of being lightweight, making it suitable for automatic lung nodule detection.

show abstract

Accurate and Efficient LIF-Nets for 3D Detection and Recognition

Cited by 8 publications

References 45 publications

BIDL: a brain-inspired deep learning framework for spatiotemporal processing

BIDL: a brain-inspired deep learning framework for spatiotemporal processing

S$^3$NN: Time Step Reduction of Spiking Surrogate Gradients for Training Energy Efficient Single-Step Spiking Neural Networks

Channel-Wise Attention Mechanism in the 3D Convolutional Network for Lung Nodule Detection

Contact Info

Product

Resources

About