BR-NPA: A non-parametric high-resolution attention model to improve the interpretability of attention
| العنوان: | BR-NPA: A non-parametric high-resolution attention model to improve the interpretability of attention |
|---|---|
| المؤلفون: | Tristan Gomez, Suiyi Ling, Thomas Fréour, Harold Mouchère |
| المساهمون: | Nantes Université - Ecole Polytechnique de l'Université de Nantes (Nantes Univ - EPUN), Nantes Université - pôle Sciences et technologie, Nantes Université (Nantes Univ)-Nantes Université (Nantes Univ), Laboratoire des Sciences du Numérique de Nantes (LS2N), Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-École Centrale de Nantes (Nantes Univ - ECN), Nantes Université (Nantes Univ)-Nantes Université (Nantes Univ)-Nantes université - UFR des Sciences et des Techniques (Nantes univ - UFR ST), Nantes Université (Nantes Univ)-Nantes Université (Nantes Univ)-Nantes Université - pôle Sciences et technologie, Nantes Université (Nantes Univ), Centre hospitalier universitaire de Nantes (CHU Nantes), Santé - François Bonamy, Université de Nantes (UN)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche en Santé de l'Université de Nantes (IRS-UN)-Centre hospitalier universitaire de Nantes (CHU Nantes), ANR-16-IDEX-0007,NExT (I-SITE),NExT (I-SITE)(2016), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Nantes Université - École Centrale de Nantes (Nantes Univ - ECN), Gomez, Tristan |
| المصدر: | Pattern Recognition Pattern Recognition, 2022, 132, pp.108927. ⟨10.1016/j.patcog.2022.108927⟩ |
| بيانات النشر: | HAL CCSD, 2022. |
| سنة النشر: | 2022 |
| مصطلحات موضوعية: | FOS: Computer and information sciences, [INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], Computer Science - Machine Learning, Artificial Intelligence, Computer Vision and Pattern Recognition (cs.CV), Signal Processing, Computer Science - Computer Vision and Pattern Recognition, Computer Vision and Pattern Recognition, Software, Machine Learning (cs.LG), [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] |
| الوصف: | International audience; The prevalence of employing attention mechanisms has brought along concerns about the interpretability of attention distributions. Although it provides insights into how a model is operating, utilizing attention as the explanation of model predictions is still highly dubious. The community is still seeking more interpretable strategies for better identifying local active regions that contribute the most to the final decision. To improve the interpretability of existing attention models, we propose a novel Bilinear Representative Non-Parametric Attention (BR-NPA) strategy that captures the task-relevant human-interpretable information. The target model is first distilled to have higher-resolution intermediate feature maps. From which, representative features are then grouped based on local pairwise feature similarity, to produce finer-grained, more precise attention maps highlighting task-relevant parts of the input. The obtained attention maps are ranked according to the activity level of the compound feature, which provides information regarding the important level of the highlighted regions. The proposed model can be easily adapted in a wide variety of modern deep models, where classification is involved. Extensive quantitative and qualitative experiments showcase more comprehensive and accurate visual explanations compared to state-of-the-art attention models and visualization methods across multiple tasks including fine-grained image classification, few-shot classification, and person re-identification, without compromising the classification accuracy. The proposed visualization model sheds imperative light on how neural networks ‘pay their attention’ differently in different tasks. |
| اللغة: | English |
| تدمد: | 0031-3203 |
| DOI: | 10.1016/j.patcog.2022.108927⟩ |
| URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dc2a7c23fc9cea4b2e4d7d92149770a2 https://hal.science/hal-03773655 |
| Rights: | OPEN |
| رقم الانضمام: | edsair.doi.dedup.....dc2a7c23fc9cea4b2e4d7d92149770a2 |
| قاعدة البيانات: | OpenAIRE |
| تدمد: | 00313203 |
|---|---|
| DOI: | 10.1016/j.patcog.2022.108927⟩ |