Progressive Learned Image Compression for Machine Perception

TL;DR

PICM-Net addresses machine perception by introducing progressive learned image compression with trit-plane coding and an adaptive decoding controller. It integrates progressive latent coding, rate-distortion prioritization, and a confidence-based decoding cutoff to balance bit rate and downstream task accuracy. The paper provides a systematic analysis of prioritization strategies and demonstrates competitive rate-accuracy performance against both human oriented progressive codecs and machine oriented non-progressive codecs on ImageNet classification. This work enables adaptable, task aware, progressive transmission suitable for bandwidth constrained machine vision deployment.

Abstract

Recent advances in learned image codecs have been extended from human perception toward machine perception. However, progressive image compression with fine granular scalability (FGS)-which enables decoding a single bitstream at multiple quality levels-remains unexplored for machine-oriented codecs. In this work, we propose a novel progressive learned image compression codec for machine perception, PICM-Net, based on trit-plane coding. By analyzing the difference between human- and machine-oriented rate-distortion priorities, we systematically examine the latent prioritization strategies in terms of machine-oriented codecs. To further enhance real-world adaptability, we design an adaptive decoding controller, which dynamically determines the necessary decoding level during inference time to maintain the desired confidence of downstream machine prediction. Extensive experiments demonstrate that our approach enables efficient and adaptive progressive transmission while maintaining high performance in the downstream classification task, establishing a new paradigm for machine-aware progressive image compression.

Figures (11)

• Figure 1: Overview of our proposed codec, PICM-Net. Our encoder produces the compressed bitstream with machine-aware prioritization, while during inference, the decoder adaptively determines the optimal decoding level based on the desired confidence of downstream machine prediction.
• Figure 2: Architecture of our proposed codec.
• Figure 3: Comparison of prioritization strategies for image classification. Each curve represents the average accuracy or cross-entropy measured across 50 randomly sampled images from the ImageNet validation set. Cross entropy in (b) is measured with pretrained ResNet50.
• Figure 4: Visualizations of reconstructed images from a single bitstream at selected quality levels.
• Figure 5: Rate--accuracy performance comparison. The left panel (a) compares ours against progressive human-oriented codecs at selected decoding levels, where the bitrate range is adjusted to reflect bitrate ranges of different codec properties. The right panel (b) compares ours against machine-oriented non-progressive codecs. The dashed lines represent non-progressive codecs, the horizontal dashed lines represent the upper bound performance on uncompressed images, and the solid lines represent progressive codecs.