Multiple Different Black Box Explanations for Image Classifiers

• URL: http://arxiv.org/abs/2309.14309v3
• Date: Tue, 13 Feb 2024 22:38:30 GMT
• Title: Multiple Different Black Box Explanations for Image Classifiers
• Authors: Hana Chockler, David A. Kelly, Daniel Kroening
• Abstract summary: We describe an algorithm and a tool, MultiReX, for computing multiple explanations of the output of a black-box image classifier for a given image. Our algorithm uses a principled approach based on causal theory. We show that MultiReX finds multiple explanations on 96% of the images in the ImageNet-mini benchmark, whereas previous work finds multiple explanations only on 11%.
• Score: 14.182742896993974
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Existing explanation tools for image classifiers usually give only a single explanation for an image's classification. For many images, however, both humans and image classifiers accept more than one explanation for the image label. Thus, restricting the number of explanations to just one is arbitrary and severely limits the insight into the behavior of the classifier. In this paper, we describe an algorithm and a tool, MultiReX, for computing multiple explanations of the output of a black-box image classifier for a given image. Our algorithm uses a principled approach based on causal theory. We analyse its theoretical complexity and provide experimental results showing that MultiReX finds multiple explanations on 96% of the images in the ImageNet-mini benchmark, whereas previous work finds multiple explanations only on 11%.

Related papers

• Causal Identification of Sufficient, Contrastive and Complete Feature Sets in Image Classification [6.338178373376447]
  We show that causal explanations enjoy the same formal properties as logic-based ones, while still lending themselves to black-box algorithms.<n>We augment the definition of explanation with confidence awareness and introduce complete causal explanations.<n>Our algorithms are efficiently computable, taking on average 6s per image on a ResNet50 model to compute all types of explanations.
  arXiv  Detail & Related papers  (2025-07-31T12:33:00Z)
• Free Argumentative Exchanges for Explaining Image Classifiers [14.761474103796203]
  We provide a solution by defining a novel method for explaining the outputs of image classifiers with debates between two agents. We obtain these debates as concrete instances of Free Argumentative eXchanges (FAXs), a novel argumentation-based multi-agent framework.
  arXiv  Detail & Related papers  (2025-02-18T16:15:36Z)
• Causal Explanations for Image Classifiers [17.736724129275043]
  We present a novel black-box approach to computing explanations grounded in the theory of actual causality. We present an algorithm for computing approximate explanations based on these definitions. We demonstrate that rex is the most efficient tool and produces the smallest explanations.
  arXiv  Detail & Related papers  (2024-11-13T18:52:42Z)
• Interpretable Measures of Conceptual Similarity by Complexity-Constrained Descriptive Auto-Encoding [112.0878081944858]
  Quantifying the degree of similarity between images is a key copyright issue for image-based machine learning. We seek to define and compute a notion of "conceptual similarity" among images that captures high-level relations. Two highly dissimilar images can be discriminated early in their description, whereas conceptually dissimilar ones will need more detail to be distinguished.
  arXiv  Detail & Related papers  (2024-02-14T03:31:17Z)
• Why do CNNs excel at feature extraction? A mathematical explanation [53.807657273043446]
  We introduce a novel model for image classification, based on feature extraction, that can be used to generate images resembling real-world datasets. In our proof, we construct piecewise linear functions that detect the presence of features, and show that they can be realized by a convolutional network.
  arXiv  Detail & Related papers  (2023-07-03T10:41:34Z)
• Minimum Description Length Clustering to Measure Meaningful Image Complexity [65.268245109828]
  We present a new image complexity metric through hierarchical clustering of patches. We use the minimum description length principle to determine the number of clusters and designate certain points as outliers and, hence, correctly assign white noise a low score.
  arXiv  Detail & Related papers  (2023-06-26T15:37:04Z)
• Two-Stage Holistic and Contrastive Explanation of Image Classification [16.303752364521454]
  A whole-output explanation can help a human user gain an overall understanding of model behaviour. We propose a contrastive whole-output explanation (CWOX) method for image classification.
  arXiv  Detail & Related papers  (2023-06-10T04:22:13Z)
• Explaining Image Classifiers with Multiscale Directional Image Representation [4.29434097275489]
  We present ShearletX, a novel mask explanation method for image classifiers based on the shearlet transform. To support our method, we propose a mathematical definition for explanation artifacts and an information theoretic score to evaluate the quality of mask explanations.
  arXiv  Detail & Related papers  (2022-11-22T09:24:45Z)
• What You See is What You Classify: Black Box Attributions [61.998683569022006]
  We train a deep network, the Explainer, to predict attributions for a pre-trained black-box classifier, the Explanandum. Unlike most existing approaches, ours is capable of directly generating very distinct class-specific masks. We show that our attributions are superior to established methods both visually and quantitatively.
  arXiv  Detail & Related papers  (2022-05-23T12:30:04Z)
• Compositional Explanations for Image Classifiers [18.24535957515688]
  We present a novel, black-box algorithm for computing explanations that uses a principled approach based on causal theory. We implement the method in the tool CET (Compositional Explanation Tool)
  arXiv  Detail & Related papers  (2021-03-05T11:54:14Z)
• Contrastive Explanations for Model Interpretability [77.92370750072831]
  We propose a methodology to produce contrastive explanations for classification models. Our method is based on projecting model representation to a latent space. Our findings shed light on the ability of label-contrastive explanations to provide a more accurate and finer-grained interpretability of a model's decision.
  arXiv  Detail & Related papers  (2021-03-02T00:36:45Z)
• This is not the Texture you are looking for! Introducing Novel Counterfactual Explanations for Non-Experts using Generative Adversarial Learning [59.17685450892182]
  counterfactual explanation systems try to enable a counterfactual reasoning by modifying the input image. We present a novel approach to generate such counterfactual image explanations based on adversarial image-to-image translation techniques. Our results show that our approach leads to significantly better results regarding mental models, explanation satisfaction, trust, emotions, and self-efficacy than two state-of-the art systems.
  arXiv  Detail & Related papers  (2020-12-22T10:08:05Z)
• Combining Similarity and Adversarial Learning to Generate Visual Explanation: Application to Medical Image Classification [0.0]
  We leverage a learning framework to produce our visual explanations method. Using metrics from the literature, our method outperforms state-of-the-art approaches. We validate our approach on a large chest X-ray database.
  arXiv  Detail & Related papers  (2020-12-14T08:34:12Z)
• Seed the Views: Hierarchical Semantic Alignment for Contrastive Representation Learning [116.91819311885166]
  We propose a hierarchical semantic alignment strategy via expanding the views generated by a single image to textbfCross-samples and Multi-level representation. Our method, termed as CsMl, has the ability to integrate multi-level visual representations across samples in a robust way.
  arXiv  Detail & Related papers  (2020-12-04T17:26:24Z)
• Focus Longer to See Better:Recursively Refined Attention for Fine-Grained Image Classification [148.4492675737644]
  Deep Neural Network has shown great strides in the coarse-grained image classification task. In this paper, we try to focus on these marginal differences to extract more representative features. Our network repetitively focuses on parts of images to spot small discriminative parts among the classes.
  arXiv  Detail & Related papers  (2020-05-22T03:14:18Z)
• Explainable Image Classification with Evidence Counterfactual [0.0]
  We introduce SEDC as a model-agnostic instance-level explanation method for image classification. For a given image, SEDC searches a small set of segments that, in case of removal, alters the classification. We compare SEDC(-T) with popular feature importance methods such as LRP, LIME and SHAP, and we describe how the mentioned importance ranking issues are addressed.
  arXiv  Detail & Related papers  (2020-04-16T08:02:48Z)
• GeoDA: a geometric framework for black-box adversarial attacks [79.52980486689287]
  We propose a framework to generate adversarial examples in one of the most challenging black-box settings. Our framework is based on the observation that the decision boundary of deep networks usually has a small mean curvature in the vicinity of data samples.
  arXiv  Detail & Related papers  (2020-03-13T20:03:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.