Single-Stage Broad Multi-Instance Multi-Label Learning (BMIML) With Diverse Inter-Correlations and Its Application to Medical Image Classification
Qi Lai, Jianhang Zhou, Yanfen Gan, Chi‐Man Vong, C. L. Philip Chen
Abstract
In real applications, one object (e.g., image) can be described by multiple instances (e.g., image patches) and simultaneously associated with multiple labels. Such applications can be formulated as <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">multi-instance multi-label learning</i> (MIML) problems and have been extensively studied currently. Existing MIML methods are useful in many applications but most of which suffer from relatively low accuracy and training efficiency due to: i) <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">the inter-label correlations</i> are neglected; ii) <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">the inter-instance correlations</i> cannot be learned directly with other types of correlations due to the missing instance labels; iii) diverse inter-correlations (e.g., inter-label correlations, inter-instance correlations) can only be learned in multiple stages. To resolve these issues, a new single-stage framework called <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">broad multi-instance multi-label learning</i> (BMIML) is proposed. In BMIML, there are three innovative modules: i) <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">auto-weighted label enhancement learning</i> (AWLEL) based on broad learning system (BLS) is designed, which simultaneously captures the inter-label correlations while traditional BLS cannot; ii) A specific MIML neural network, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">scalable multi-instance probabilistic regression</i> (SMIPR) is constructed to effectively estimate the inter-instance correlations, which can provide additional probabilistic information for learning; iii) Finally, an <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">interactive decision optimization</i> (IDO) is designed to combine and optimize the results from AWLEL and SMIPR and form a single-stage framework. Consequently, BMIML can achieve simultaneous learning of diverse inter-correlations between whole images, instances, and labels in single stage for higher classification accuracy and much faster training time. Experiments show that BMIML is highly competitive to (or even better than) existing methods in accuracy and much faster.