SpikeDet reaches 52.2% AP on COCO 2017 with spiking networks by optimizing firing patterns via MDSNet and SMFM, using half the energy of prior SNN detectors.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 2polarities
background 2representative citing papers
LSFormer uses local structure-aware spiking self-attention and spiking response pooling to cut global attention bottlenecks, delivering 4.3% and 8.6% accuracy gains on Tiny-ImageNet and N-CALTECH101 over prior transformer-based SNNs.
The Hodgkin-Huxley model is contractive without input and under sufficiently sparse impulsive synaptic inputs, making spike timings reliable in the contracting regime.
The paper reviews and extends energy-based dynamical models that use gradient flows and energy landscapes for neurocomputation, learning, and optimization tasks.
A literature survey of FPGA-based digital neuromorphic architectures over 25 years that creates a taxonomy of architectural features, lists advantages and disadvantages, and identifies trends.
citing papers explorer
-
SpikeDet: Better Firing Patterns for Accurate and Energy-Efficient Object Detection with Spiking Neural Networks
SpikeDet reaches 52.2% AP on COCO 2017 with spiking networks by optimizing firing patterns via MDSNet and SMFM, using half the energy of prior SNN detectors.
-
Breaking Global Self-Attention Bottlenecks in Transformer-based Spiking Neural Networks with Local Structure-Aware Self-Attention
LSFormer uses local structure-aware spiking self-attention and spiking response pooling to cut global attention bottlenecks, delivering 4.3% and 8.6% accuracy gains on Tiny-ImageNet and N-CALTECH101 over prior transformer-based SNNs.
-
On the Contraction of Excitable Systems
The Hodgkin-Huxley model is contractive without input and under sufficiently sparse impulsive synaptic inputs, making spike timings reliable in the contracting regime.
-
Energy-Based Dynamical Models for Neurocomputation, Learning, and Optimization
The paper reviews and extends energy-based dynamical models that use gradient flows and energy landscapes for neurocomputation, learning, and optimization tasks.
-
A Quarter of a Century of Neuromorphic Architectures on FPGAs -- an Overview
A literature survey of FPGA-based digital neuromorphic architectures over 25 years that creates a taxonomy of architectural features, lists advantages and disadvantages, and identifies trends.