DeepAI AI Chat
Log In Sign Up

Multi Instance Learning For Unbalanced Data

by   Mark Kozdoba, et al.

In the context of Multi Instance Learning, we analyze the Single Instance (SI) learning objective. We show that when the data is unbalanced and the family of classifiers is sufficiently rich, the SI method is a useful learning algorithm. In particular, we show that larger data imbalance, a quality that is typically perceived as negative, in fact implies a better resilience of the algorithm to the statistical dependencies of the objects in bags. In addition, our results shed new light on some known issues with the SI method in the setting of linear classifiers, and we show that these issues are significantly less likely to occur in the setting of neural networks. We demonstrate our results on a synthetic dataset, and on the COCO dataset for the problem of patch classification with weak image level labels derived from captions.


Deep multi-class learning from label proportions

We propose a learning algorithm capable of learning from label proportio...

An embarrassingly simple approach to neural multiple instance classification

Multiple Instance Learning (MIL) is a weak supervision learning paradigm...

MOC-GAN: Mixing Objects and Captions to Generate Realistic Images

Generating images with conditional descriptions gains increasing interes...

EC3: Combining Clustering and Classification for Ensemble Learning

Classification and clustering algorithms have been proved to be successf...

DGMIL: Distribution Guided Multiple Instance Learning for Whole Slide Image Classification

Multiple Instance Learning (MIL) is widely used in analyzing histopathol...

Domain Adaptive Multiple Instance Learning for Instance-level Prediction of Pathological Images

Pathological image analysis is an important process for detecting abnorm...