Spike2Former: Efficient Spiking Transformer for High-performance Image Segmentation
This addresses the low-power advantage of SNNs for image segmentation tasks, representing a strong specific gain in this domain.
The paper tackled the poor performance of Spiking Neural Networks (SNNs) in image segmentation by proposing Spike2Former, which improved spike firing and training stability, achieving state-of-the-art results with significant gains such as +12.7% mIoU on ADE20K.
Spiking Neural Networks (SNNs) have a low-power advantage but perform poorly in image segmentation tasks. The reason is that directly converting neural networks with complex architectural designs for segmentation tasks into spiking versions leads to performance degradation and non-convergence. To address this challenge, we first identify the modules in the architecture design that lead to the severe reduction in spike firing, make targeted improvements, and propose Spike2Former architecture. Second, we propose normalized integer spiking neurons to solve the training stability problem of SNNs with complex architectures. We set a new state-of-the-art for SNNs in various semantic segmentation datasets, with a significant improvement of +12.7% mIoU and 5.0 efficiency on ADE20K, +14.3% mIoU and 5.2 efficiency on VOC2012, and +9.1% mIoU and 6.6 efficiency on CityScapes.