Related papers: Towards Better Understanding Attribution Methods
This paper studies the robustness of feature attribution methods for deep neural networks. It challenges the current notion of attributional robustness that largely ignores the difference in the model's outputs and introduces a new way of…
Attribution-based explanations are garnering increasing attention recently and have emerged as the predominant approach towards \textit{eXplanable Artificial Intelligence}~(XAI). However, the absence of consistent configurations and…
Modern deep learning models are notoriously opaque, which has motivated the development of methods for interpreting how deep models predict. This goal is usually approached with attribution method, which assesses the influence of features…
Feature attribution methods attempt to explain neural network predictions by identifying relevant features. However, establishing a cohesive framework for assessing feature attribution remains a challenge. There are several views through…
Revealing the transparency of Deep Neural Networks (DNNs) has been widely studied to describe the decision mechanisms of network inner structures. In this paper, we propose a novel post-hoc framework, Unfold and Conquer Attribution Guidance…
Fairness has been a critical issue that affects the adoption of deep learning models in real practice. To improve model fairness, many existing methods have been proposed and evaluated to be effective in their own contexts. However, there…
Deep networks have shown remarkable performance across a wide range of tasks, yet getting a global concept-level understanding of how they function remains a key challenge. Many post-hoc concept-based approaches have been introduced to…
Understanding the decision processes of deep vision models is essential for their safe and trustworthy deployment in real-world settings. Existing explainability approaches, such as saliency maps or concept-based analyses, often suffer from…
Attribution methods compute importance scores for input features to explain model predictions. However, assessing the faithfulness of these methods remains challenging due to the absence of attribution ground truth to model predictions. In…
In the last decade neural network have made huge impact both in industry and research due to their ability to extract meaningful features from imprecise or complex data, and by achieving super human performance in several domains. However,…
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…
Deep neural networks can predict human judgments, but this does not imply that they rely on human-like information or reveal the cues underlying those judgments. Prior work has addressed this issue using attribution heatmaps, but their…
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…
To better understand the output of deep neural networks (DNN), attribution based methods have been an important approach for model interpretability, which assign a score for each input dimension to indicate its importance towards the model…
Attribution methods have been developed to understand the decision-making process of machine learning models, especially deep neural networks, by assigning importance scores to individual features. Existing attribution methods often built…
Neural networks have shown remarkable performance in computer vision, but their deployment in numerous scientific and technical fields is challenging due to their black-box nature. Scientists and practitioners need to evaluate the…
Interpreting the decisions of complex computer vision models is crucial to establish trust and accountability, especially in safety-critical domains. An established approach to interpretability is generating visual attribution maps that…
The attribution method provides a direction for interpreting opaque neural networks in a visual way by identifying and visualizing the input regions/pixels that dominate the output of a network. Regarding the attribution method for visually…
For AI systems to garner widespread public acceptance, we must develop methods capable of explaining the decisions of black-box models such as neural networks. In this work, we identify two issues of current explanatory methods. First, we…
Recent work has found that adversarially-robust deep networks used for image classification are more interpretable: their feature attributions tend to be sharper, and are more concentrated on the objects associated with the image's…