This Looks Like That: Deep Learning for Interpretable Image Recognition

How researchers see this paper

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

Neural Prototype Trees for Interpretable Fine-grained Image Recognition (2020, methodology): “Similar to ProtoPNet [9], we replace each prototype pn ∈ P with its nearest latent patch present in the training data, z̃ n.”
This Looks Like That, Because ... Explaining Prototypes for Interpretable Image Recognition (2020, methodology): “The following section summarizes the ProtoPNet model [11].”
Interpretable and Steerable Sequence Learning via Prototypes (2019, background): “Recently the concept has been incorporated in convolutional neural networks to build interpretable image classifiers [6, 19].”
AUC Maximization in the Era of Big Data and AI: A Survey (2022, background): “Two issues are of foremost importance, namely fairness [7, 10, 20, 113] and interpretability [3, 24, 64].”
A Comprehensive Survey on Applications of Transformers for Deep Learning Tasks (2023, methodology): “By understanding these useful features, a model can recognize the specific object from the other available object in the image or video (Zhao et al., 2019, Jiao et al., 2019, Hénaff, 2020, Chen et al., 2019a).”
Interpretable deep learning: interpretation, interpretability, trustworthiness, and beyond (2021, background): “Chen et al. [35] proposedProtoPNet,which explains the deep model by finding prototypical parts of predicted objects and gathering evidence from the prototypes to make final decisions.”