SpikeCLIP: A Contrastive Language-Image Pretrained Spiking Neural Network
Keywords: Spiking Neural Networks (SNNs), Multimodal, Image classification
TL;DR: A Contrastive Language-Image Pretrained Spiking Neural Network
Abstract: Spiking neural networks (SNNs) have demonstrated the capability to achieve comparable performance to deep neural networks (DNNs) in both visual and linguistic domains while offering the advantages of improved energy efficiency and adherence to biological plausibility. However, the extension of such single-modality SNNs into the realm of multimodal scenarios remains an unexplored territory. Drawing inspiration from the concept of contrastive image-language pre-training (CLIP), we introduce a novel framework, named SpikeCLIP, to address the gap between two modalities within the context of spike-based computing through a two-step recipe involving ''Alignment Pre-training'' followed by ''Dual-Loss Fine-tuning''. Extensive experimentation demonstrates that SNNs achieve comparable results to their DNN counterparts while significantly reducing energy consumption across a variety of datasets commonly used for multimodal model evaluation. Furthermore, SpikeCLIP maintains robust performance in image classification tasks that involve class labels not predefined within specific categories.
Supplementary Material: zip
Primary Area: general machine learning (i.e., none of the above)
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 560
Loading