Multi-instance embedding learning with deconfounded instance-level prediction

Confounded information is an objective fact when using multi-instance learning (MIL) to classify bags of instances, which may be inherited by MIL embedding methods and lead questionable bag label prediction. To respond this problem, we propose the with deconfounded instance-level prediction algorithm. Unlike traditional embedding-based strategies, design a optimization goal maximize distinction between instances in positive negative bags. In addition, present use bag-level feature distillation reduce classification task single-instance problem. Under theoretical analysis, cohesiveness magnitude metrics are developed explain benefits proposed technique settings. Extensive experiments on thirty-four data sets demonstrate that our method has best overall performance over other state-of-the-art methods. This strategy, particular, substantial advantage web sets. Source codes available at https://github.com/InkiInki/MEDI .