In Defense of LSTMs for Addressing Multiple Instance Learning Problems

Abstract

LSTMs have a proven track record in analyzing sequential data. But what about unordered instance bags, as found under a Multiple Instance Learning (MIL) setting? While not often used for this, we show LSTMs excell under this setting too. In addition, we show thatLSTMs are capable of indirectly capturing instance-level information us-ing only bag-level annotations. Thus, they can be used to learn instance-level models in a weakly supervised manner. Our empirical evaluation on both simplified (MNIST) and realistic (Lookbook and Histopathology) datasets shows that LSTMs are competitive with or even surpass state-of-the-art methods specially designed for handling specific MIL problems. Moreover, we show that their performance on instance-level prediction is close to that of fully-supervised methods.

arXiv commentaccepted in ACCV 2020 (oral)

References in corpus (12)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Sequence to Sequence Learning with Neural Networks
• Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
• Learning deep representations by mutual information estimation and maximization
• Multiple Instance Learning: A Survey of Problem Characteristics and Applications
• Attention-based Deep Multiple Instance Learning
• Revisiting Multiple Instance Neural Networks
• Rank Pooling for Action Recognition
• Co-occurrence Feature Learning for Skeleton based Action Recognition using Regularized Deep LSTM Networks
• Quality Aware Network for Set to Set Recognition
• Multiple instance learning with graph neural networks
• Learning and Interpreting Multi-Multi-Instance Learning Networks