2 papers
cs.CV2026
CrossMambaTuning: Synergistic Spatial and Cross-Layer Adaptation for Machine Vision Compression
Haobo Xiong, Shaobo Liu, Kai Liu +1
To reduce deployment cost and retraining overhead, adapting pretrained learned image compression (LIC) models to downstream machine vision tasks has attracted growing attention. Ho…
cs.CV2026
What and Where to Adapt: Structure-Semantics Co-Tuning for Machine Vision Compression via Synergistic Adapters
Shaobo Liu, Haobo Xiong, Kai Liu +1
Parameter-efficient fine-tuning of pre-trained codecs is a promising direction in image compression for human and machine vision. While most existing works have primarily focused o…