Classify small images accurately using little memory and CPU with ImageSig
Classify small images accurately using little memory and CPU with ImageSig
ImageSig: A signature transform for ultra-lightweight image recognition
arXiv paper abstract https://arxiv.org/abs/2205.06929v1
arXiv PDF paper https://arxiv.org/pdf/2205.06929v1.pdf
This paper introduces a new lightweight method for image recognition.
ImageSig is based on computing signatures and does not require a convolutional structure or an attention-based encoder.
... achieves: a) an accuracy for 64 X 64 RGB images that exceeds many of the state-of-the-art methods and simultaneously b) requires orders of magnitude less FLOPS, power and memory footprint.
... pretrained model ... as small as 44.2 KB in size ... shows unprecedented performance on ... Raspberry Pi and Jetson-nano.
ImageSig treats images as streams with multiple channels. These streams are parameterized by spatial directions.
... could have many of these "detectors" assembled on the same chip ...
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comments