Exploiting Richness of Learned Compressed Representation of Images for Semantic Segmentation
This addresses bandwidth and latency issues for autonomous vehicles and ADAS in data transmission to cloud servers, but it is incremental as it builds on existing compression and segmentation methods.
The paper tackles the problem of latency in autonomous vehicle data pipelines by using a learning-based compression codec that allows semantic segmentation directly on compressed representations, achieving a compression factor up to 66x and reducing overall compute by 11% with a dice coefficient of 0.84 compared to 0.88 using decompressed images.
Autonomous vehicles and Advanced Driving Assistance Systems (ADAS) have the potential to radically change the way we travel. Many such vehicles currently rely on segmentation and object detection algorithms to detect and track objects around its surrounding. The data collected from the vehicles are often sent to cloud servers to facilitate continual/life-long learning of these algorithms. Considering the bandwidth constraints, the data is compressed before sending it to servers, where it is typically decompressed for training and analysis. In this work, we propose the use of a learning-based compression Codec to reduce the overhead in latency incurred for the decompression operation in the standard pipeline. We demonstrate that the learned compressed representation can also be used to perform tasks like semantic segmentation in addition to decompression to obtain the images. We experimentally validate the proposed pipeline on the Cityscapes dataset, where we achieve a compression factor up to $66 \times$ while preserving the information required to perform segmentation with a dice coefficient of $0.84$ as compared to $0.88$ achieved using decompressed images while reducing the overall compute by $11\%$.