Related papers: Less is More: Fewer Interpretable Region via Submo…

To develop a trustworthy AI system, which aim to identify the input regions that most influence the models decisions. The primary task of existing attribution methods lies in efficiently and accurately identifying the relationships among…

This work explores the novel idea of learning a submodular scoring function to improve the specificity/selectivity of existing feature attribution methods. Submodular scores are natural for attribution as they are known to accurately model…

As deep vision models' popularity rapidly increases, there is a growing emphasis on explanations for model predictions. The inherently explainable attribution method aims to enhance the understanding of model behavior by identifying the…

Few-shot Semantic Segmentation (FSS) is a challenging task that utilizes limited support images to segment associated unseen objects in query images. However, recent FSS methods are observed to perform worse, when enlarging the number of…

Many computer vision systems require low-cost segmentation algorithms based on deep learning, either because of the enormous size of input images or limited computational budget. Common solutions uniformly downsample the input images to…

Scene recognition, particularly for aerial and underwater images, often suffers from various types of degradation, such as blurring or overexposure. Previous works that focus on convolutional neural networks have been shown to be able to…

Subset selection-based methods are widely used to explain deep vision models: they attribute predictions by highlighting the most influential image regions and support object-level explanations. While these methods perform well in…

Image attribution analysis seeks to highlight the feature representations learned by visual models such that the highlighted feature maps can reflect the pixel-wise importance of inputs. Gradient integration is a building block in the…

Modern datasets span billions of samples, making training on all available data infeasible. Selecting a high quality subset helps in reducing training costs and enhancing model quality. Submodularity, a discrete analogue of convexity, is…

Rule sets are highly interpretable logical models in which the predicates for decision are expressed in disjunctive normal form (DNF, OR-of-ANDs), or, equivalently, the overall model comprises an unordered collection of if-then decision…

Attribution maps are one of the most established tools to explain the functioning of computer vision models. They assign importance scores to input features, indicating how relevant each feature is for the prediction of a deep neural…

The deployment of Machine Learning models intraoperatively for tissue characterisation can assist decision making and guide safe tumour resections. For image classification models, pixel attribution methods are popular to infer…

Data attribution methods play a crucial role in understanding machine learning models, providing insight into which training data points are most responsible for model outputs during deployment. However, current state-of-the-art approaches…

The limited transparency of the inner decision-making mechanism in deep neural networks (DNN) and other machine learning (ML) models has hindered their application in several domains. In order to tackle this issue, feature attribution…

In the field of artificial intelligence, AI models are frequently described as `black boxes' due to the obscurity of their internal mechanisms. It has ignited research interest on model interpretability, especially in attribution methods…

Self-Explainable Models (SEMs) rely on Prototypical Concept Learning (PCL) to enable their visual recognition processes more interpretable, but they often struggle in data-scarce settings where insufficient training samples lead to…

Feature attribution maps are a popular approach to highlight the most important pixels in an image for a given prediction of a model. Despite a recent growth in popularity and available methods, little attention is given to the objective…

Few-shot learning (FSL) presents a challenging learning problem in which only a few samples are available for each class. Decision interpretation is more important in few-shot classification due to a greater chance of error compared to…

While large text-to-image models are able to synthesize "novel" images, these images are necessarily a reflection of the training data. The problem of data attribution in such models -- which of the images in the training set are most…

The discovery of new objects in modern wide-field asteroid and comet surveys can be enhanced by first identifying observations belonging to known solar system objects. The assignation of new observations to a known object is an attribution…