3 papers
cs.NE2024
A More Accurate Approximation of Activation Function with Few Spikes Neurons
Dayena Jeong, Jaewoo Park, Jeonghee Jo +5
Recent deep neural networks (DNNs), such as diffusion models [1], have faced high computational demands. Thus, spiking neural networks (SNNs) have attracted lots of attention as en…
cs.NE2023
Gradient Scaling on Deep Spiking Neural Networks with Spike-Dependent Local Information
Seongsik Park, Jeonghee Jo, Jongkil Park +9
Deep spiking neural networks (SNNs) are promising neural networks for their model capacity from deep neural network architecture and energy efficiency from SNNs' operations. To tra…
cs.CV2023
SimFLE: Simple Facial Landmark Encoding for Self-Supervised Facial Expression Recognition in the Wild
Jiyong Moon, Seongsik Park
One of the key issues in facial expression recognition in the wild (FER-W) is that curating large-scale labeled facial images is challenging due to the inherent complexity and ambi…