Jul 2026
Is It Time for the Renaissance of Salient Object Detection in the Era of MLLMs?
FOCUS couples top-down Bayesian-surprise calibration of protocol-conditioned foreground granularity with bottom-up propagation of MLLMs evidence over entity-centric perceptual manifolds induced by self-supervised features, yielding coherent object extents as prompts for a general segmenter.
Wen-Zhuo Zhao, Xiuzhi Li, Z. Mao et al.
· arXiv.org · 1 citation