# Balancing Bias and Variance for Active Weakly Supervised Learning

arXiv: https://arxiv.org/abs/2206.05682 · HTML: https://mlsanity.com/paper/2206.05682/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 30 references that are in the map.
- First posted on arXiv 12 Jun 2022.

## Builds on (most cited first, 11 of 11)

- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning](https://mlsanity.com/paper/1906.08158/) (2019)
- [Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding](https://mlsanity.com/paper/1511.02680/) (2015)
- [Cost-Effective Active Learning for Deep Image Classification](https://mlsanity.com/paper/1701.03551/) (2017)
- [Multiple Instance Learning: A Survey of Problem Characteristics and Applications](https://mlsanity.com/paper/1612.03365/) (2016)
- [Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference](https://mlsanity.com/paper/1506.02158/) (2015)
- [Variance-based regularization with convex objectives](https://mlsanity.com/paper/1610.02581/) (2016)
- [Multiple instance active learning for object detection](https://mlsanity.com/paper/2104.02324/) (2021)
- [Reinforced active learning for image segmentation](https://mlsanity.com/paper/2002.06583/) (2020)

## Built on by (most cited first, 1 of 1)

- [Controllable Textual Inversion for Personalized Text-to-Image Generation](https://mlsanity.com/paper/2304.05265/) (2023)

## Abstract (arXiv)

As a widely used weakly supervised learning scheme, modern multiple instance learning (MIL) models achieve competitive performance at the bag level. However, instance-level prediction, which is essential for many important applications, remains largely unsatisfactory. We propose to conduct novel active deep multiple instance learning that samples a small subset of informative instances for annotation, aiming to significantly boost the instance-level prediction. A variance regularized loss function is designed to properly balance the bias and variance of instance-level predictions, aiming to effectively accommodate the highly imbalanced instance distribution in MIL and other fundamental challenges. Instead of directly minimizing the variance regularized loss that is non-convex, we optimize a distributionally robust bag level likelihood as its convex surrogate. The robust bag likelihood provides a good approximation of the variance based MIL loss with a strong theoretical guarantee. It also automatically balances bias and variance, making it effective to identify the potentially positive instances to support active sampling. The robust bag likelihood can be naturally integrated with a deep architecture to support deep model training using mini-batches of positive-negative bag pairs. Finally, a novel P-F sampling function is developed that combines a probability vector and predicted instance scores, obtained by optimizing the robust bag likelihood. By leveraging the key MIL assumption, the sampling function can explore the most challenging bags and effectively detect their positive instances for annotation, which significantly improves the instance-level prediction. Experiments conducted over multiple real-world datasets clearly demonstrate the state-of-the-art instance-level prediction achieved by the proposed model.