Related papers: CAM-Based Methods Can See through Walls
Transparency and explainability in image classification are essential for establishing trust in machine learning models and detecting biases and errors. State-of-the-art explainability methods generate saliency maps to show where a specific…
Deep learning models have great potential in medical imaging, including orthodontics and skeletal maturity assessment. However, applying a model to data different from its training set can lead to unreliable predictions that may impact…
With the intervention of machine vision in our crucial day to day necessities including healthcare and automated power plants, attention has been drawn to the internal mechanisms of convolutional neural networks, and the reason why the…
Classification networks can be used to localize and segment objects in images by means of class activation maps (CAMs). However, without pixel-level annotations, classification networks are known to (1) mainly focus on discriminative…
Interpretation of deep learning remains a very challenging problem. Although the Class Activation Map (CAM) is widely used to interpret deep model predictions by highlighting object location, it fails to provide insight into the salient…
Deep Neural Networks have often been called the black box because of the complex, deep architecture and non-transparency presented by the inner layers. There is a lack of trust to use Artificial Intelligence in critical and high-precision…
Convolutional neural networks have become state-of-the-art in a wide range of image recognition tasks. The interpretation of their predictions, however, is an active area of research. Whereas various interpretation methods have been…
The Convolutional Neural Network (CNN) is a widely used deep learning architecture for computer vision. However, its black box nature makes it difficult to interpret the behavior of the model. To mitigate this issue, AI practitioners have…
Despite their black-box nature, deep learning models are extensively used in image-based drug discovery to extract feature vectors from single cells in microscopy images. To better understand how these networks perform representation…
With the growing demand for interpretable deep learning models, this paper introduces Integrative CAM, an advanced Class Activation Mapping (CAM) technique aimed at providing a holistic view of feature importance across Convolutional Neural…
The interpretability of medical image analysis models is considered a key research field. We use a dataset of eye-tracking data from five radiologists to compare the outputs of interpretability methods and the heatmaps representing where…
As AI-based medical devices are becoming more common in imaging fields like radiology and histology, interpretability of the underlying predictive models is crucial to expand their use in clinical practice. Existing heatmap-based…
Input perturbation methods occlude parts of an input to a function and measure the change in the function's output. Recently, input perturbation methods have been applied to generate and evaluate saliency maps from convolutional neural…
Class attribution maps (CAMs) provide local explanations for the decisions of convolutional neural networks. While widely used in practice, the evaluation of CAMs remains challenging due to the lack of ground-truth explanations, making it…
We present Smooth Grad-CAM++, a technique which combines two recent techniques: SMOOTHGRAD and Grad-CAM++. Smooth Grad-CAM++ has the capability of either visualizing a layer, subset of feature maps, or subset of neurons within a feature map…
Class activation map (CAM) has been widely studied for visual explanation of the internal working mechanism of convolutional neural networks. The key of existing CAM-based methods is to compute effective weights to combine activation maps…
The gradient-weighted class activation mapping (Grad-CAM) method can faithfully highlight important regions in images for deep model prediction in image classification, image captioning and many other tasks. It uses the gradients in…
One of the significant challenges of deep neural networks is that the complex nature of the network prevents human comprehension of the outcome of the network. Consequently, the applicability of complex machine learning models is limited in…
Poor generalization is one symptom of models that learn to predict target variables using spuriously-correlated image features present only in the training distribution instead of the true image features that denote a class. It is often…
Explainable Deep Learning has gained significant attention in the field of artificial intelligence (AI), particularly in domains such as medical imaging, where accurate and interpretable machine learning models are crucial for effective…