REVIEW 4 cited by
Post-Training Quantization for Cross-Platform Learned Image Compression
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
It has been witnessed that learned image compression has outperformed conventional image coding techniques and tends to be practical in industrial applications. One of the most critical issues that need to be considered is the non-deterministic calculation, which makes the probability prediction cross-platform inconsistent and frustrates successful decoding. We propose to solve this problem by introducing well-developed post-training quantization and making the model inference integer-arithmetic-only, which is much simpler than presently existing training and fine-tuning based approaches yet still keeps the superior rate-distortion performance of learned image compression. Based on that, we further improve the discretization of the entropy parameters and extend the deterministic inference to fit Gaussian mixture models. With our proposed methods, the current state-of-the-art image compression models can infer in a cross-platform consistent manner, which makes the further development and practice of learned image compression more promising.
Forward citations
Cited by 4 Pith papers
-
MLVC: Multi-platform Learned Video Codec for Real-World Deployment
MLVC transmits entropy scale parameters via the hyperprior so that neural video decoding stays deterministic across different NPU vendors, achieving >70% BD-rate (MOS) gains over hardware HEVC in video-conferencing tests.
-
Learning Switchable Priors for Neural Image Compression
A finite set of trainable priors, selected by predicted indices, decouples entropy coding complexity from the probabilistic model family in neural image compression, enabling faster and lighter codecs that still beat BPG.
-
HAMP-LIC: Hessian-Aware Mixed-Precision Post-Training Quantization for Learned Image Compression
A Hessian-aware mixed-precision post-training quantization framework for learned image compression reports 4.85x weight compression with BD-rate losses around 0.59 to 1.79 percent on standard test sets.
-
Generalized Gaussian Model for Learned Image Compression
A generalized Gaussian entropy model with a learned shape parameter and two training fixes improves rate-distortion performance of learned image codecs compared to Gaussian and mixture models.
Discussion (0). Continue with ORCID to comment.