BR-NPA: A Non-Parametric High-Resolution Attention Model to improve the Interpretability of Attention

Gomez, Tristan; Ling, Suiyi; Fréour, Thomas; Mouchère, Harold

doi:10.48550/arxiv.2106.02566

Cited by 2 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The last attention model included in this study is called Bilinear Representative Non-Parametric Attention (BR-NPA) [13] and proposes to generate attention maps to guide the model spatially without any dedicated parameter, contrary to the models mentioned above which feature either a convolution attention module or parametric prototypes.…”

Section: Saliency Map Generation Approachesmentioning

confidence: 99%

Comparison of attention models and post-hoc explanation methods for embryo stage identification: a case study

Gomez¹,

Fréour²,

Mouchère³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

An important limitation to the development of AI-based solutions for In Vitro Fertilization (IVF) is the black-box nature of most state-of-the-art models, due to the complexity of deep learning architectures, which raises potential bias and fairness issues. The need for interpretable AI has risen not only in the IVF field but also in the deep learning community in general. This has started a trend in literature where authors focus on designing objective metrics to evaluate generic explanation methods. In this paper, we study the behavior of recently proposed objective faithfulness metrics applied to the problem of embryo stage identification. We benchmark attention models and post-hoc methods using metrics and further show empirically that (1) the metrics produce low overall agreement on the model ranking and (2) depending on the metric approach, either post-hoc methods or attention models are favored. We conclude with general remarks about the difficulty of defining faithfulness and the necessity of understanding its relationship with the type of approach that is favored.

show abstract

Section: Saliency Map Generation Approachesmentioning

confidence: 99%