EAC adaptively selects subsets of quantized latent features for multiple machine vision tasks and uses tiny per-task adapters, improving machine task accuracy at lower bitrates without retraining the base codec.
Towards end-to-end image compression and analysis with transformers,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
An Efficient Adaptive Compression Method for Human Perception and Machine Vision Tasks
EAC adaptively selects subsets of quantized latent features for multiple machine vision tasks and uses tiny per-task adapters, improving machine task accuracy at lower bitrates without retraining the base codec.