# Kernel Self-Attention in Deep Multiple Instance Learning

arXiv: https://arxiv.org/abs/2005.12991 · HTML: https://mlsanity.com/paper/2005.12991/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 May 2020.

## Built on by (most cited first, 2 of 2)

- [Giga-SSL: Self-Supervised Learning for Gigapixel Images](https://mlsanity.com/paper/2212.03273/) (2022)
- [Attention, Please! Revisiting Attentive Probing Through the Lens of Efficiency](https://mlsanity.com/paper/2506.10178/) (2025)

## Abstract (arXiv)

Not all supervised learning problems are described by a pair of a fixed-size input tensor and a label. In some cases, especially in medical image analysis, a label corresponds to a bag of instances (e.g. image patches), and to classify such bag, aggregation of information from all of the instances is needed. There have been several attempts to create a model working with a bag of instances, however, they are assuming that there are no dependencies within the bag and the label is connected to at least one instance. In this work, we introduce Self-Attention Attention-based MIL Pooling (SA-AbMILP) aggregation operation to account for the dependencies between instances. We conduct several experiments on MNIST, histological, microbiological, and retinal databases to show that SA-AbMILP performs better than other models. Additionally, we investigate kernel variations of Self-Attention and their influence on the results.