Related papers: Combining Similarity and Adversarial Learning to G…

Knowledge of what spatial elements of medical images deep learning methods use as evidence is important for model interpretability, trustiness, and validation. There is a lack of such techniques for models in regression tasks. We propose a…

Understanding why a classification model prefers one class over another for an input instance is the challenge of contrastive explanation. This work implements concept-based contrastive explanations for image classification by leveraging…

We propose a novel approach to mitigate biases in computer vision models by utilizing counterfactual generation and fine-tuning. While counterfactuals have been used to analyze and address biases in DNN models, the counterfactuals…

The use of deep learning in computer vision tasks such as image classification has led to a rapid increase in the performance of such systems. Due to this substantial increment in the utility of these systems, the use of artificial…

As machine learning methods see greater adoption and implementation in high stakes applications such as medical image diagnosis, the need for model interpretability and explanation has become more critical. Classical approaches that assess…

The identification of lesion within medical image data is necessary for diagnosis, treatment and prognosis. Segmentation and classification approaches are mainly based on supervised learning with well-paired image-level or voxel-level…

As machine learning algorithms are increasingly applied to high impact yet high risk tasks, such as medical diagnosis or autonomous driving, it is critical that researchers can explain how such algorithms arrived at their predictions. In…

Due to their complex nature, it is hard to characterize the ways in which machine learning models can misbehave or be exploited when deployed. Recent work on adversarial examples, i.e. inputs with minor perturbations that result in…

Deep Learning algorithms have achieved the state-of-the-art performance for Image Classification and have been used even in security-critical applications, such as biometric recognition systems and self-driving cars. However, recent works…

Variational auto-encoders (VAEs) provide an attractive solution to image generation problem. However, they tend to produce blurred and over-smoothed images due to their dependence on pixel-wise reconstruction loss. This paper introduces a…

''Making black box models explainable'' is a vital problem that accompanies the development of deep learning networks. For networks taking visual information as input, one basic but challenging explanation method is to identify and…

Supervised learning is ubiquitous in medical image analysis. In this paper we consider the problem of meta-learning -- predicting which methods will perform well in an unseen classification problem, given previous experience with other…

As digital medical imaging becomes more prevalent and archives increase in size, representation learning exposes an interesting opportunity for enhanced medical decision support systems. On the other hand, medical imaging data is often…

Explainability is a longstanding challenge in deep learning, especially in high-stakes domains like healthcare. Common explainability methods highlight image regions that drive an AI model's decision. Humans, however, heavily rely on…

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 grows, so too does the…

The ambiguity of the decision-making process has been pointed out as the main obstacle to applying the deep learning-based method in a practical way in spite of its outstanding performance. Interpretability could guarantee the confidence of…

An effective way to obtain different perspectives on any given topic is by conducting a debate, where participants argue for and against the topic. Here, we propose a novel debate framework for understanding and explaining a continuous…

Adversarial examples are maliciously tweaked images that can easily fool machine learning techniques, such as neural networks, but they are normally not visually distinguishable for human beings. One of the main approaches to solve this…

Ascription of an image gives insights into the objects that influence the classification of the whole image or its pixels towards a specific category. These insights help radiologists to visualize deformities in medical imaging. Most of the…

Adversarial training has been shown as an effective approach to improve the robustness of image classifiers against white-box attacks. However, its effectiveness against black-box attacks is more nuanced. In this work, we demonstrate that…