Address Instance-level Label Prediction in Multiple Instance Learning
This addresses a limitation in MIL for tasks requiring instance-level predictions, such as medical imaging or object detection, by enabling accurate label assignment without instance-level supervision, though it is an incremental improvement over existing MIL methods.
The paper tackles the problem of predicting instance-level labels in Multiple Instance Learning (MIL), where only bag-level labels are available, by proposing a novel algorithm with an instance-level loss. The result shows that the algorithm achieves superior instance-level performance and comparable bag-level performance to state-of-the-art methods, with empirical validation indicating it can match fully supervised models trained with instance labels.
\textit{Multiple Instance Learning} (MIL) is concerned with learning from bags of instances, where only bag labels are given and instance labels are unknown. Existent approaches in this field were mainly designed for the bag-level label prediction (predict labels for bags) but not the instance-level (predict labels for instances), with the task loss being only defined at the bag level. This restricts their application in many tasks, where the instance-level labels are more interested. In this paper, we propose a novel algorithm, whose loss is specifically defined at the instance level, to address instance-level label prediction in MIL. We prove that the loss of this algorithm can be unbiasedly and consistently estimated without using instance labels, under the i.i.d assumption. Empirical study validates the above statements and shows that the proposed algorithm can achieve superior instance-level and comparative bag-level performance, compared to state-of-the-art MIL methods. In addition, it shows that the proposed method can achieve similar results as the fully supervised model (trained with instance labels) for label prediction at the instance level.