Yang Sun

General image fusion aims at integrating important in-formation from multi-source images. However, due to the significant cross-task gap, the respective fusion mechanism varies considerably in practice, resulting in limited performance across subtasks. To handle this problem, we pro-pose a novel task-customized mixture of adapters (TC-MoA) for general image fusion, adaptively prompting various fusion tasks in a unified model. We borrow the insight from the mixture of experts (MoE), taking the experts as effi-cient tuning adapters to prompt a pre-trained foundation model. These adapters are shared across different tasks and constrained by mutual information regularization, ensuring compatibility with different tasks while complementarity for multi-source images. The task-specific routing networks customize these adapters to extract task-specific information from different sources with dynamic dominant inten-sity, performing adaptive visual feature prompt fusion. No-tably, our TC-MoA controls the dominant intensity bias for different fusion tasks, successfully unifying multiple fusion tasks in a single model. Extensive experiments show that TC-MoA outperforms the competing approaches in learning commonalities while retaining compatibility for gen-eral image fusion (multi-modal, multi-exposure, and multi-focus), and also demonstrating striking controllability on more generalization experiments. The code is available at https://github.com/YangSun22/TC-MoA.

Introduction Northeast China has always been an area with severe brucellosis prevalence. This study will identify Brucella in Northeast China and test its resistance to antibiotics, in order to clarify its resistance mechanism. Brucella is a widespread and highly pathogenic bacteria that poses serious threats to public health and animal husbandry. Methods In this study, 61 Brucella isolates were identified by abortus-melitensis-ovis-suis polymerase chain reaction (AMOS-PCR) for biotypes and epidemic potential was clarified by multi-locus sequence analysis. Whole-genome sequencing (WGS) was performed and the antibiotic susceptibility of the Brucella strains against 13 antibiotics was detected with the use of E-test strips. Results The results showed that all of the isolates were Brucella melitensis ST8, group CC4 with little genetic variation and obvious geographical characteristics. All 61 Brucella isolates were sensitive to doxycycline, tetracycline, minocycline, levofloxacin, ciprofloxacin, gentamicin, and streptomycin, while 24.6%, 86.9%, 65.6%, 27.9%, 3.3%, and 1.6% were resistant to rifampin, azithromycin, cefepime, cefoperazone/sulbactam, cefotaxime, and meperidine/sulfamethoxazole, respectively. This is the first report of cephalosporin-resistant B. melitensis in China. The WGS results indicated that about 60% of the antibiotic resistance genes were associated with efflux pumps (mainly the resistance nodulation division family). Discussion Brucellosis is usually treated with antibiotics for several months, which can easily lead to the emergence of antibiotic resistance. To ensure the effectiveness and safety of antibiotics for treatment of brucellosis, continuous surveillance of antibiotic susceptibility is especially important.