Pixel-Unshuffled Multi-level Feature Map Compression for FCVCM

Younhee Kim, Se-Yoon Jeong, Jooyoung Lee, Jongseok Lee, Minsub Kim

Abstract: The feature compression process for machine tasks involves several steps: feeding a video into the task network, extracting intermediate feature maps, compressing these maps into a bitstream on the client side, transmitting the bitstream to a resource-rich server, decoding it, and ultimately completing the specific machine task. In this paper, we present a multi-level feature compression method designed for machine tasks. We introduce an efficient and effective feature reshaping and merging module within the PCA-based feature coding scheme. This module utilizes pixel-unshuffled operations to reshape the multi-level features, merges them into a single map, and then performs a transformation. Our proposed method achieves a BD-rate gain of 49.69% and 66.3% in comparison to the previous computational low cost PCA-based feature coding method for object detection and instance segmentation tasks, respectively.