Generalizing GradCAM for Embedding Networks
Visualizing CNN is an important part in building trust and explaining model's prediction. Methods like CAM and GradCAM have been really successful in localizing area of the image responsible for the output but are only limited to classification models. In this paper, we present a new method EmbeddingCAM, which generalizes the Grad-CAM for embedding networks. We show that for classification networks, EmbeddingCAM reduces to GradCAM. We show the effectiveness of our method on CUB-200-2011 dataset and also present quantitative and qualitative analysis on the dataset.
Code (1)
Tasks
ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Enhancing Explainable AI: A Hybrid Approach Combining GradCAM and LRP for CNN Interpretability
We present a new technique that explains the output of a CNN-based model using a combination of GradCAM and LRP methods. Both of these methods produce visual explanations by highlighting input regions that are important …
DiffGradCAM: A Universal Class Activation Map Resistant to Adversarial Training
Class Activation Mapping (CAM) and its gradient-based variants (e.g., GradCAM) have become standard tools for explaining Convolutional Neural Network (CNN) predictions. However, these approaches typically focus on indivi…
MRxaI: Black-Box Explainability for Image Classifiers in a Medical Setting
Existing tools for explaining the output of image classifiers can be divided into white-box, which rely on access to the model internals, and black-box, agnostic to the model. As the usage of AI in the medical domain gro…
How to Manipulate CNNs to Make Them Lie: the GradCAM Case
Recently many methods have been introduced to explain CNN decisions. However, it has been shown that some methods can be sensitive to manipulation of the input. We continue this line of work and investigate the explanati…
Improving Mass Detection in Mammography Images: A Study of Weakly Supervised Learning and Class Activation Map Methods
In recent years, weakly supervised models have aided in mass detection using mammography images, decreasing the need for pixel-level annotations. However, most existing models in the literature rely on Class Activation M…
Weakly-supervised Learning