Search Results for author:
Found 5 papers, 0 papers with code
A Principled Hierarchical Deep Learning Approach to Joint Image Compression and Classification
Our goal is to optimize DL models such that the encoder latent requires low channel bandwidth while still delivers feature information for high classification accuracy.
End-to-End Optimization of JPEG-Based Deep Learning Process for Image Classification
Among major deep learning (DL) applications, distributed learning involving image classification require effective image compression codecs deployed on low-cost sensing devices for efficient transmission and storage.
End-to-end optimized image compression for multiple machine tasks
An increasing share of captured images and videos are transmitted for storage and remote analysis by computer vision algorithms, rather than to be viewed by humans.
End-to-end optimized image compression for machines, a study
An increasing share of image and video content is analyzed by machines rather than viewed by humans, and therefore it becomes relevant to optimize codecs for such applications where the analysis is performed remotely.
Faster and Accurate Classification for JPEG2000 Compressed Images in Networked Applications
Furthermore, we show that traditional augmentation transforms such as flipping/shifting are ineffective in the DWT domain and present different augmentation transformations to achieve more accurate classification without any additional cost.
