# BLADE: ReliaBle Dynamic Hardware-Aware SNN-ANN Boundary SeLection for Event-BAseD Object DEtection

arXiv: https://arxiv.org/abs/2609.17562 · HTML: https://mlsanity.com/paper/2609.17562/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 37 references that are in the map.
- First posted on arXiv 22 Jul 2026.

## Builds on (most cited first, 21 of 21)

- [BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks](https://mlsanity.com/paper/1709.01686/) (2017)
- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [SkipNet: Learning Dynamic Routing in Convolutional Networks](https://mlsanity.com/paper/1711.09485/) (2017)
- [BlockDrop: Dynamic Inference Paths in Residual Networks](https://mlsanity.com/paper/1711.08393/) (2017)
- [Recurrent Vision Transformers for Object Detection with Event Cameras](https://mlsanity.com/paper/2212.05598/) (2022)
- [A Large Scale Event-based Detection Dataset for Automotive](https://mlsanity.com/paper/2001.08499/) (2020)
- [SEENN: Towards Temporal Spiking Early-Exit Neural Networks](https://mlsanity.com/paper/2304.01230/) (2023)
- [Fully neuromorphic vision and control for autonomous drone flight](https://mlsanity.com/paper/2303.08778/) (2023)
- [Hybrid SNN-ANN: Energy-Efficient Classification and Object Detection for Event-Based Vision](https://mlsanity.com/paper/2112.03423/) (2021)
- [SMamba: Sparse Mamba for Event-based Object Detection](https://mlsanity.com/paper/2501.11971/) (2025)
- [SoftSNN: Low-Cost Fault Tolerance for Spiking Neural Network Accelerators under Soft Errors](https://mlsanity.com/paper/2203.05523/) (2022)
- [DeepAxe: A Framework for Exploration of Approximation and Reliability Trade-offs in DNN Accelerators](https://mlsanity.com/paper/2303.08226/) (2023)
- [Optimising Event-Driven Spiking Neural Network with Regularisation and Cutoff](https://mlsanity.com/paper/2301.09522/) (2023)
- [Efficient Event-Based Object Detection: A Hybrid Neural Network with Spatial and Temporal Attention](https://mlsanity.com/paper/2403.10173/) (2024)
- [SAFFIRA: a Framework for Assessing the Reliability of Systolic-Array-Based DNN Accelerators](https://mlsanity.com/paper/2403.02946/) (2024)
- [Best of Both Worlds: Hybrid SNN-ANN Architecture for Event-based Optical Flow Estimation](https://mlsanity.com/paper/2306.02960/) (2023)
- [Towards Efficient Deployment of Hybrid SNNs on Neuromorphic and Edge AI Hardware](https://mlsanity.com/paper/2407.08704/) (2024)
- [SpikeFI: A Fault Injection Framework for Spiking Neural Networks](https://mlsanity.com/paper/2412.06795/) (2024)
- [Effective and Memory-Efficient Alternatives to ECC for Reliable Large-Scale DNNs](https://mlsanity.com/paper/2605.07417/) (2026)
- [Spatial-Temporal Search for Spiking Neural Networks](https://mlsanity.com/paper/2410.18580/) (2024)
- [An FPGA-Based SoC Architecture with a RISC-V Controller for Energy-Efficient Temporal-Coding Spiking Neural Networks](https://mlsanity.com/paper/2603.18054/) (2026)

## Abstract (arXiv)

Hybrid Spiking Neural Network (SNN)-Artificial Neural Network (ANN) architectures combine the energy efficiency of SNNs with the superior detection accuracy of ANNs for event-based object detection. Existing hybrid SNN--ANN networks, however, employ static inference and select the SNN-ANN boundary primarily according to accuracy and energy consumption, without considering dynamic inference or reliability. This paper presents BLADE, the first reliability-aware boundary selection methodology for dynamic hybrid SNN-ANN networks with ANN early exit. The proposed framework jointly optimizes the SNN-ANN boundary and ANN early-exit configuration according to reliability, detection accuracy, execution time, and energy consumption, while incorporating reliability through hierarchical statistical fault injection during design-space exploration. Experimental evaluation on an event-based object detector achieves an mAP 0.5 of 0.691 while reducing the inference compute energy to 15.82~mJ when the ANN early exit fires. Reliability analysis identifies the most significant floating-point exponent bit as the dominant source of catastrophic failures, producing significant-or-worse accuracy degradation in 58.8% of its fault injections. Protecting this single bit with approximately 3% storage overhead eliminates catastrophic failures across the evaluated realistic technology fault rates. Furthermore, increasing the proportion of SNN computation improves fault tolerance, with the fully SNN configuration achieving a reliability retention of 0.965 under aggressive fault conditions. The results demonstrate that jointly optimizing reliability, accuracy, execution time, and energy consumption enables more dependable deployment of dynamic hybrid SNN--ANN systems for safety-critical edge AI applications.