CoCoX: Generating Conceptual and Counterfactual Explanations via Fault-Lines

@inproceedings{Akula2020CoCoXGC,
  title={CoCoX: Generating Conceptual and Counterfactual Explanations via Fault-Lines},
  author={Arjun Reddy Akula and Shuai Wang and Song-Chun Zhu},
  booktitle={AAAI},
  year={2020}
}
We present CoCoX (short for Conceptual and Counterfactual Explanations), a model for explaining decisions made by a deep convolutional neural network (CNN). In Cognitive Psychology, the factors (or semantic-level features) that humans zoom in on when they imagine an alternative to a model prediction are often referred to as fault-lines. Motivated by this, our CoCoX model explains decisions made by a CNN using fault-lines. Specifically, given an input image I for which a CNN classification model… Expand
CX-ToM: Counterfactual Explanations with Theory-of-Mind for Enhancing Human Trust in Image Recognition Models
TLDR
It is argued that, due to the iterative, conceptual and counterfactual nature of CX-ToM explanations, the framework is practical and more natural for both expert and non-expert users to understand the internal workings of complex deep learning models. Expand
Mind the Context: The Impact of Contextualization in Neural Module Networks for Grounding Visual Referring Expressions
TLDR
This work substantially reduces the number of modules in NMN by up to 75% by parameterizing the module arguments, and proposes a method to contextualize the parameterized model to enhance the module’s capacity in exploiting the visiolinguistic associations. Expand
ECINN: Efficient Counterfactuals from Invertible Neural Networks
TLDR
A method is proposed, ECINN, that utilizes the generative capacities of invertible neural networks for image classification to generate counterfactual examples efficiently and outperforms established methods that generate heatmap-based explanations. Expand
Explaining Deep Neural Networks
TLDR
This thesis investigates two major directions for explaining deep neural networks: self-explanatory neural models that generate natural language explanations and models that have a built-in module that generates explanations for the predictions of the model. Expand
A general approach for Explanations in terms of Middle Level Features
TLDR
This paper suggests developing an XAI general approach that allows producing explanations for an ML system behaviour in terms of different and user-selected input features, i.e., explanations composed of input properties that the human user can select according to his background knowledge and goals. Expand
Contrastive explanation: a structural-model approach
  • Tim Miller
  • Computer Science
  • The Knowledge Engineering Review
  • 2021
TLDR
This model can help researchers in subfields of artificial intelligence to better understand contrastive explanation and is demonstrated on two classical problems in artificial intelligence: classification and planning. Expand
An exact counterfactual-example-based approach to tree-ensemble models interpretability
TLDR
A positive answer is found for any model that enters the category of tree ensemble models, which encompasses a wide range of models dedicated to massive heterogeneous industrial data processing such as XGBoost, Catboost, Lightgbm, random forests, which could derive an exact geometrical characterisation of the decision regions under the form of a collection of multidimensional intervals. Expand
Counterfactual explanation of Bayesian model uncertainty
TLDR
This paper compares the counterfactual explanation of models based on Bayesian uncertainty and softmax score and predicts minimal important features, which maximally change classifier output to explain the decision-making process of the Bayesian model. Expand
C3: Compositional Counterfactual Constrastive Learning for Video-grounded Dialogues
TLDR
A novel approach of Compositional Counterfactual Contrastive Learning is proposed to develop contrastive training between factual and counterfactual samples in video-grounded dialogues and focuses on contrastive hidden state representations among compositional output tokens to optimize the representation space in a generation setting. Expand
Comprehensible Counterfactual Explanation on Kolmogorov-Smirnov Test
TLDR
This paper proposes the notion of most comprehensible counterfactual explanations, which accommodates both the KS test data and the user domain knowledge in producing explanations, and develops an efficient algorithm MOCHE (for MOst CompreHensible Explanation) that avoids enumerating and checking an exponential number of subsets of the test set failing theKS test. Expand
...
1
2
...

References

SHOWING 1-10 OF 34 REFERENCES
Generating Counterfactual Explanations with Natural Language
TLDR
This work considers a fine-grained image classification task and proposes an intuitive method to generate counterfactual explanations by inspecting which evidence in an input is missing, but might contribute to a different classification decision if present in the image. Expand
Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives
TLDR
A novel method that provides contrastive explanations justifying the classification of an input by a black box classifier such as a deep neural network is proposed and it is argued that such explanations are natural for humans and are used commonly in domains such as health care and criminology. Expand
Generating Visual Explanations
TLDR
A new model is proposed that focuses on the discriminating properties of the visible object, jointly predicts a class label, and explains why the predicted label is appropriate for the image, and generates sentences that realize a global sentence property, such as class specificity. Expand
Natural Language Interaction with Explainable AI Models
TLDR
This paper presents an explainable AI (XAI) system that provides explanations for its predictions, and identifies several correlations between user's questions and the XAI answers using Youtube Action dataset. Expand
Counterfactual Visual Explanations
TLDR
It is found that users trained to distinguish bird species fare better when given access to counterfactual explanations in addition to training examples, and the effectiveness of these explanations in teaching humans is explored. Expand
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
TLDR
This work proposes a technique for producing ‘visual explanations’ for decisions from a large class of Convolutional Neural Network (CNN)-based models, making them more transparent and explainable, and shows that even non-attention based models learn to localize discriminative regions of input image. Expand
Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)
TLDR
Concept Activation Vectors (CAVs) are introduced, which provide an interpretation of a neural net's internal state in terms of human-friendly concepts, and may be used to explore hypotheses and generate insights for a standard image classification network as well as a medical application. Expand
Automating Interpretability: Discovering and Testing Visual Concepts Learned by Neural Networks
TLDR
DTCAV (Discovery TCAV) is introduced, a global concept-based interpretability method that can automatically discover concepts as image segments, along with each concept's estimated importance for a deep neural network's predictions, and it is validated that discovered concepts are as coherent to humans as hand-labeled concepts. Expand
Axiomatic Attribution for Deep Networks
We study the problem of attributing the prediction of a deep network to its input features, a problem previously studied by several other works. We identify two fundamental axioms— Sensitivity andExpand
Explainable AI as Collaborative Task Solving
TLDR
Compared to the most popularly used attribution based explanations (saliency maps), the new framework X-ToM significantly improves human trust in the underlying vision system and quantitatively evaluates human’s trust of machine behaviors. Expand
...
1
2
3
4
...