US Patent Application 17918080. INPUT IMAGE SIZE SWITCHABLE NETWORK FOR ADAPTIVE RUNTIME EFFICIENT IMAGE CLASSIFICATION simplified abstract
INPUT IMAGE SIZE SWITCHABLE NETWORK FOR ADAPTIVE RUNTIME EFFICIENT IMAGE CLASSIFICATION
Organization Name
Inventor(s)
INPUT IMAGE SIZE SWITCHABLE NETWORK FOR ADAPTIVE RUNTIME EFFICIENT IMAGE CLASSIFICATION - A simplified explanation of the abstract
- This abstract for appeared for US patent application number 17918080 Titled 'INPUT IMAGE SIZE SWITCHABLE NETWORK FOR ADAPTIVE RUNTIME EFFICIENT IMAGE CLASSIFICATION'
Simplified Explanation
The abstract discusses various techniques for implementing and training image classification networks. These techniques involve using shared convolutional layers for input images of any resolution and selectively applying normalization based on the image resolution. The abstract also mentions training methods such as mixed image size parallel training and mixed image size ensemble distillation.
Original Abstract Submitted
Techniques related to implementing and training image classification networks are discussed. Such techniques include applying shared convolutional layers to input images regardless of resolution and applying normalization selectively based on the input image resolution. Such techniques further include training using mixed image size parallel training and mixed image size ensemble distillation.