Learned Image Compression for Machine Perception

• Main Authors: Codevilla, Felipe, Simard, Jean Gabriel, Goroshin, Ross, Pal, Chris
• Format: Journal Article
• Language: English
• Published: 03-11-2021
• Subjects: Computer Science - Computer Vision and Pattern Recognition
• DOI: 10.48550/arxiv.2111.02249

Recent work has shown that learned image compression strategies can
outperform standard hand-crafted compression algorithms that have been
developed over decades of intensive research on the rate-distortion trade-off.
With growing applications of computer vision, high quality image reconstruction
from a compressible representation is often a secondary objective. Compression
that ensures high accuracy on computer vision tasks such as image segmentation,
classification, and detection therefore has the potential for significant
impact across a wide variety of settings. In this work, we develop a framework
that produces a compression format suitable for both human perception and
machine perception. We show that representations can be learned that
simultaneously optimize for compression and performance on core vision tasks.
Our approach allows models to be trained directly from compressed
representations, and this approach yields increased performance on new tasks
and in low-shot learning settings. We present results that improve upon
segmentation and detection performance compared to standard high quality JPGs,
but with representations that are four to ten times smaller in terms of bits
per pixel. Further, unlike naive compression methods, at a level ten times
smaller than standard JEPGs, segmentation and detection models trained from our
format suffer only minor degradation in performance.