# But that's not why: Inference adjustment by interactive prototype revision

arXiv: https://arxiv.org/abs/2203.10087 · HTML: https://mlsanity.com/paper/2203.10087/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 25 references that are in the map.
- First posted on arXiv 18 Mar 2022.

## Builds on (most cited first, 14 of 14)

- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [Understanding the Role of Individual Units in a Deep Neural Network](https://mlsanity.com/paper/2009.05041/) (2020)
- [Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictions](https://mlsanity.com/paper/1710.04806/) (2017)
- [Neural Prototype Trees for Interpretable Fine-grained Image Recognition](https://mlsanity.com/paper/2012.02046/) (2020)
- [Robust Classification with Convolutional Prototype Learning](https://mlsanity.com/paper/1805.03438/) (2018)
- [How to represent part-whole hierarchies in a neural network](https://mlsanity.com/paper/2102.12627/) (2021)
- [Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes](https://mlsanity.com/paper/2111.15000/) (2021)
- [DeepIGeoS: A Deep Interactive Geodesic Framework for Medical Image Segmentation](https://mlsanity.com/paper/1707.00652/) (2017)
- [Interpretable Image Recognition with Hierarchical Prototypes](https://mlsanity.com/paper/1906.10651/) (2019)
- [Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation](https://mlsanity.com/paper/2106.11958/) (2021)
- [Iteratively-Refined Interactive 3D Medical Image Segmentation with Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1911.10334/) (2019)
- [Deep Interactive Learning: An Efficient Labeling Approach for Deep Learning-Based Osteosarcoma Treatment Response Assessment](https://mlsanity.com/paper/2007.01383/) (2020)

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

- [Interactive Medical Image Analysis with Concept-based Similarity Reasoning](https://mlsanity.com/paper/2503.06873/) (2025)

## Abstract (arXiv)

Despite significant advances in machine learning, decision-making of artificial agents is still not perfect and often requires post-hoc human interventions. If the prediction of a model relies on unreasonable factors it is desirable to remove their effect. Deep interactive prototype adjustment enables the user to give hints and correct the model's reasoning. In this paper, we demonstrate that prototypical-part models are well suited for this task as their prediction is based on prototypical image patches that can be interpreted semantically by the user. It shows that even correct classifications can rely on unreasonable prototypes that result from confounding variables in a dataset. Hence, we propose simple yet effective interaction schemes for inference adjustment: The user is consulted interactively to identify faulty prototypes. Non-object prototypes can be removed by prototype masking or a custom mode of deselection training. Interactive prototype rejection allows machine learning na"ive users to adjust the logic of reasoning without compromising the accuracy.