Search Results for author:
Found 19 papers, 10 papers with code
Feature Accentuation: Revealing 'What' Features Respond to in Natural Images
Most research has primarily centered around attribution methods, which provide explanations in the form of heatmaps, showing where the model directs its attention for a given feature.
On the Foundations of Shortcut Learning
Deep-learning models can extract a rich assortment of features from data.
Saliency strikes back: How filtering out high frequencies improves white-box explanations
Attribution methods correspond to a class of explainability methods (XAI) that aim to assess how individual inputs contribute to a model's decision-making process.
Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization
However, its widespread adoption has been limited due to a reliance on tricks to generate interpretable images, and corresponding challenges in scaling it to deeper neural networks.
Adversarial alignment: Breaking the trade-off between the strength of an attack and its relevance to human perception
Harmonized DNNs achieve the best of both worlds and experience attacks that are detectable and affect features that humans find diagnostic for recognition, meaning that attacks on these models are more likely to be rendered ineffective by inducing similar effects on human perception.
COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP tasks
COCKATIEL is a novel, post-hoc, concept-based, model-agnostic XAI technique that generates meaningful explanations from the last layer of a neural net model trained on an NLP classification task by using Non-Negative Matrix Factorization (NMF) to discover the concepts the model leverages to make predictions and by exploiting a Sensitivity Analysis to estimate accurately the importance of each of these concepts for the model.
Explainable Artificial Intelligence (XAI)
Sentiment Analysis
Confident Object Detection via Conformal Prediction and Conformal Risk Control: an Application to Railway Signaling
Deploying deep learning models in real-world certified systems requires the ability to provide confidence estimates that accurately reflect their uncertainty.
Diffusion Models as Artists: Are we Closing the Gap between Humans and Machines?
An important milestone for AI is the development of algorithms that can produce drawings that are indistinguishable from those of humans.
Conformal Prediction for Trustworthy Detection of Railway Signals
We present an application of conformal prediction, a form of uncertainty quantification with guarantees, to the detection of railway signals.
CRAFT: Concept Recursive Activation FacTorization for Explainability
However, recent research has exposed the limited practical value of these methods, attributed in part to their narrow focus on the most prominent regions of an image -- revealing "where" the model looks, but failing to elucidate "what" the model sees in those areas.
Harmonizing the object recognition strategies of deep neural networks with humans
Across 84 different DNNs trained on ImageNet and three independent datasets measuring the where and the how of human visual strategies for object recognition on those images, we find a systematic trade-off between DNN categorization accuracy and alignment with human visual strategies for object recognition.
Conviformers: Convolutionally guided Vision Transformer
Vision transformers are nowadays the de-facto choice for image classification tasks.
Ranked #1 on
Fine-Grained Image Classification
on Herbarium 2022
On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective
Input gradients have a pivotal role in a variety of applications, including adversarial attack algorithms for evaluating model robustness, explainable AI techniques for generating Saliency Maps, and counterfactual explanations. However, Saliency Maps generated by traditional neural networks are often noisy and provide limited insights.
Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure
HSIC measures the dependence between regions of an input image and the output of a model based on kernel embeddings of distributions.
Xplique: A Deep Learning Explainability Toolbox
Today's most advanced machine-learning models are hardly scrutable.
Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysis
A variety of methods have been proposed to try to explain how deep neural networks make their decisions.
What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methods
A multitude of explainability methods and associated fidelity performance metrics have been proposed to help better understand how modern AI systems make decisions.
Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis
We describe a novel attribution method which is grounded in Sensitivity Analysis and uses Sobol indices.
How Good is your Explanation? Algorithmic Stability Measures to Assess the Quality of Explanations for Deep Neural Networks
A plethora of methods have been proposed to explain how deep neural networks reach their decisions but comparatively, little effort has been made to ensure that the explanations produced by these methods are objectively relevant.
