4 papers
Model Merging to Evolution: Parameter Space Exploration for Expert Models
Chao Wang, Yuchen Guo, Zheng Tan +4
Model merging integrates the capabilities of multiple expert models to create strong models for multiple tasks without additional training, thereby reducing computational resource…
Seeking Consensus: Geometric-Semantic On-the-Fly Recalibration for Open-Vocabulary Remote Sensing Semantic Segmentation
Guanchun Wang, Chenxiao Wu, Xiangrong Zhang +4
Open-vocabulary semantic segmentation (OVSS) in remote sensing images is a promising task that employs textual descriptions for identifying undefined land cover categories. Despite…
Task-free Adaptive Meta Black-box Optimization
Chao Wang, Licheng Jiao, Lingling Li +4
Handcrafted optimizers become prohibitively inefficient for complex black-box optimization (BBO) tasks. MetaBBO addresses this challenge by meta-learning to automatically configure…
ACMamba: Fast Unsupervised Anomaly Detection via An Asymmetrical Consensus State Space Model
Guanchun Wang, Xiangrong Zhang, Yifei Zhang +4
Unsupervised anomaly detection in hyperspectral images (HSI), aiming to detect unknown targets from backgrounds, is challenging for earth surface monitoring. However, current studi…