Joint ANN-SNN Co-training for Object Localization and Image Segmentation
This work addresses the need for low-power alternatives to deep ANNs in machine learning, though it appears incremental as it builds on existing conversion methods.
The paper tackled the problem of improving the performance of converted spiking neural networks (SNNs) for object detection and image segmentation by proposing a novel hybrid ANN-SNN co-training framework, resulting in demonstrated effectiveness in achieving design goals.
The field of machine learning has been greatly transformed with the advancement of deep artificial neural networks (ANNs) and the increased availability of annotated data. Spiking neural networks (SNNs) have recently emerged as a low-power alternative to ANNs due to their sparsity nature. In this work, we propose a novel hybrid ANN-SNN co-training framework to improve the performance of converted SNNs. Our approach is a fine-tuning scheme, conducted through an alternating, forward-backward training procedure. We apply our framework to object detection and image segmentation tasks. Experiments demonstrate the effectiveness of our approach in achieving the design goals.