Related papers: CAM-Based Methods Can See through Walls
Due to the black-box nature of deep learning models, there is a recent development of solutions for visual explanations of CNNs. Given the high cost of user studies, metrics are necessary to compare and evaluate these different methods. In…
Planet-scale photo geolocalization involves the intricate task of estimating the geographic location depicted in an image purely based on its visual features. While deep learning models, particularly convolutional neural networks (CNNs),…
An increasing number of digital images are being shared and accessed through websites, media, and social applications. Many of these images have been modified and are not authentic. Recent advances in the use of deep convolutional neural…
Neural network quantization is a critical technique for deploying models on resource-limited devices. Despite its widespread use, the impact of quantization on model perceptual fields, particularly in relation to class activation maps…
Saliency methods are a popular class of feature attribution explanation methods that aim to capture a model's predictive reasoning by identifying "important" pixels in an input image. However, the development and adoption of these methods…
Evaluating, explaining, and visualizing high-level concepts in generative models, such as variational autoencoders (VAEs), is challenging in part due to a lack of known prediction classes that are required to generate saliency maps in…
Deep neural networks (DNNs) have achieved remarkable success across domains but remain difficult to interpret, limiting their trustworthiness in high-stakes applications. This paper focuses on deep vision models, for which a dominant line…
We propose a general framework called Network Dissection for quantifying the interpretability of latent representations of CNNs by evaluating the alignment between individual hidden units and a set of semantic concepts. Given any CNN model,…
In this study, we propose a novel method to measure bottom-up saliency maps of natural images. In order to eliminate the influence of top-down signals, backward masking is used to make stimuli (natural images) subjectively invisible to…
We propose a CNN based technique that aggregates feature maps from its multiple layers that can localize abnormalities with greater details as well as predict pathology under consideration. Existing class activation mapping (CAM) techniques…
In this paper, we propose a data-free method of extracting Impressions of each class from the classifier's memory. The Deep Learning regime empowers classifiers to extract distinct patterns (or features) of a given class from training data,…
Lack of explainability in artificial intelligence, specifically deep neural networks, remains a bottleneck for implementing models in practice. Popular techniques such as Gradient-weighted Class Activation Mapping (Grad-CAM) provide a…
This paper addresses the visualization task of deep learning models. To improve Class Activation Mapping (CAM) based visualization method, we offer two options. First, we propose Gaussian upsampling, an improved upsampling method that can…
Convolutional neural networks (CNNs) define the current state-of-the-art for image recognition. With their emerging popularity, especially for critical applications like medical image analysis or self-driving cars, confirmability is…
There is great interest in "saliency methods" (also called "attribution methods"), which give "explanations" for a deep net's decision, by assigning a "score" to each feature/pixel in the input. Their design usually involves…
Neural networks for image classification tasks assume that any given image during inference belongs to one of the training classes. This closed-set assumption is challenged in real-world applications where models may encounter inputs of…
Advances in image-based dietary assessment methods have allowed nutrition professionals and researchers to improve the accuracy of dietary assessment, where images of food consumed are captured using smartphones or wearable devices. These…
Saliency methods are a common class of machine learning interpretability techniques that calculate how important each input feature is to a model's output. We find that, with the rapid pace of development, users struggle to stay informed of…
Artificial intelligence (AI) systems power the world we live in. Deep neural networks (DNNs) are able to solve tasks in an ever-expanding landscape of scenarios, but our eagerness to apply these powerful models leads us to focus on their…
Saliency methods have been widely used to highlight important input features in model predictions. Most existing methods use backpropagation on a modified gradient function to generate saliency maps. Thus, noisy gradients can result in…