Multi-Instance Learning With Emerging Novel Class

By Xiu-Shen Wei, Han-Jia Ye, Xin Mu, Jianxin Wu, Chunhua Shen, Zhi-Hua Zhou. 2021

31 citations recorded by the source corpus.

Diverse applications involving complicated data objects such as proteins and images are solved by applying multi-instance learning (MIL) algorithms. However, few MIL algorithms can deal with problems in an open and dynamic environment, where new categories of samples emerge. In this type of emerging novel class setting, algorithms should be able to not only classify the samples from the observed classes accurately, but also recognize the samples from the novel class. In this paper, we focus on the Multi-Instance learning with Emerging Novel class (MIEN) problem, and formulate MIEN from a metric learning perspective. We extract key instances to form the “super-bag” for each observed class, and non-key instances from all the observed classes to form a “meta super-bag”. Based on these super-bags, we propose the MIEN-metric method to learn discriminative metrics for classifying MIL bags from the observed classes and recognizing bags from the novel class. Experimental results of diverse domains, e.g., biological function annotation, text categorization, and object-centric/scene-centric image classification, show MIEN-metric outperforms other baseline methods significantly when the novel class emerges. Meanwhile, MIEN-metric is comparable with state-of-the-art MIL algorithms for binary classification in the traditional MIL setting.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Han-Jia Ye
2. De-chuan Zhan
3. Da-Wei Zhou
4. Qiwen Wang
5. Ziwei Liu
6. Wei-Lun Chao
7. Fu-Yun Wang
8. Zhiyuan Qi

In Computer Vision and Pattern Recognition

1. Han-Jia Ye
2. De-chuan Zhan
3. Da-Wei Zhou
4. Qiwen Wang
5. Ziwei Liu
6. Wei-Lun Chao
7. Fu-Yun Wang
8. Jun Zhu

Citations in the corpus

• Learning Placeholders for Open-Set Recognition (2021, background): “The problem of out-ofdistribution detection [10, 17, 1], anomaly detection [4, 18, 25] and novelty detection [11, 32, 41, 21, 43] are related topics to open-set recognition.”
• Learning to Classify With Incremental New Class (2021, unknown): “While these methods ignore an important issue of streaming data, namely the emergence of unknown category instances [4], [5], [6], [7], [8], e.”