Grad-CAM: Why did you say that? Visual Explanations from Deep Networks via Gradient-based Localization
By Ramprasaath R. Selvaraju, Abhishek Das, Ramakrishna Vedantam, Michael Cogswell, Devi Parikh, Dhruv Batra. 2016
1,698 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition, Safety, Robustness & Interpretability
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Trevor Darrell
- Dacheng Tao
- Jitendra Malik
- Xiaogang Wang
- Andrea Vedaldi
- Ming-Hsuan Yang
- Cordelia Schmid
In Safety, Robustness & Interpretability
- Been Kim
- K. Müller
- Riccardo Guidotti
- Dino Pedreschi
- Wojciech Samek
- Longo Luca
- Giulia Vilone
- Marco F. Huber
Citations in the corpus
- Learning Visual N-Grams from Web Data (2016, methodology): “Discriminative regions of five n-grams for three images, computed using class activation mapping [48, 70].”
- SentiNet: Detecting Localized Universal Attacks Against Deep Learning Systems (2018, methodology): “Finally, SentiNet uses the off-the-shelf implementations of Grad-CAM [46] and selective search [55].”
- Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI (2019, neutral): “Doshi-Velez, 2017; Selvaraju et al., 2016; Sheh, 2017; Symeonidis, Nanopoulos, and Manolopoulos, 2009; Tapaswi et al., 2016; Williams et al., 2016).”
- A Survey of Methods for Explaining Black Box Models (2018, background): “Their solution is not black box agnostic limited to NN, but it requires specific architectural modifications [139] or access to intermediate layers [106].”
- Adversarial Examples: Attacks and Defenses for Deep Learning (2017, background): “Many studies have been proposed to explain and interpret deep neural networks [70], [84], [119], [122].”
- Beyond Sparsity: Tree Regularization of Deep Models for Interpretability (2017, background): “Other post-hoc interpretations typically typically evaluate the sensitivity of predictions to local perturbations of inputs or the input gradient (Ribeiro, Singh, and Guestrin 2016; Selvaraju et al. 2016; Adler et al. 2016; Lundberg and Lee 2016; Erhan et al. 2009).”
- A unified view of gradient-based attribution methods for Deep Neural Networks (2017, background): “Grad-CAM [16] for CNNs) or activation functions (ie.”