Search Results for author:
Found 21 papers, 10 papers with code
Understanding Deep Networks via Extremal Perturbations and Smooth Masks
In this paper, we discuss some of the shortcomings of existing approaches to perturbation analysis and address them by introducing the concept of extremal perturbations, which are theoretically grounded and interpretable.
Interpretable Explanations of Black Boxes by Meaningful Perturbation
As machine learning algorithms are increasingly applied to high impact yet high risk tasks, such as medical diagnosis or autonomous driving, it is critical that researchers can explain how such algorithms arrived at their predictions.
There and Back Again: Revisiting Backpropagation Saliency Methods
Saliency methods seek to explain the predictions of a model by producing an importance map across each input sample.
On Compositions of Transformations in Contrastive Self-Supervised Learning
In the image domain, excellent representations can be learned by inducing invariance to content-preserving transformations via noise contrastive learning.
Net2Vec: Quantifying and Explaining how Concepts are Encoded by Filters in Deep Neural Networks
By studying such embeddings, we are able to show that 1., in most cases, multiple filters are required to code for a concept, that 2., often filters are not concept specific and help encode multiple concepts, and that 3., compared to single filter activations, filter embeddings are able to better characterize the meaning of a representation and its relationship to other concepts.
HIVE: Evaluating the Human Interpretability of Visual Explanations
As AI technology is increasingly applied to high-impact, high-risk domains, there have been a number of new methods aimed at making AI models more human interpretable.
Interactive Visual Feature Search
Many visualization techniques have been created to explain the behavior of computer vision models, but they largely consist of static diagrams that convey limited information.
Overlooked factors in concept-based explanations: Dataset choice, concept learnability, and human capability
Second, we find that concepts in the probe dataset are often less salient and harder to learn than the classes they claim to explain, calling into question the correctness of the explanations.
Debiasing Convolutional Neural Networks via Meta Orthogonalization
While deep learning models often achieve strong task performance, their successes are hampered by their inability to disentangle spurious correlations from causative factors, such as when they use protected attributes (e. g., race, gender, etc.)
Contextual Semantic Interpretability
Once the attributes are learned, they can be re-combined to reach the final decision and provide both an accurate prediction and an explicit reasoning behind the CNN decision.
Using Human Brain Activity to Guide Machine Learning
The effectiveness of this approach points to a path forward for a new class of hybrid machine learning algorithms which take both inspiration and direct constraints from neuronal data.
NormGrad: Finding the Pixels that Matter for Training
In this paper, we are rather interested by the locations of an image that contribute to the model's training.
Occlusions for Effective Data Augmentation in Image Classification
Deep networks for visual recognition are known to leverage "easy to recognise" portions of objects such as faces and distinctive texture patterns.
Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims
With the recent wave of progress in artificial intelligence (AI) has come a growing awareness of the large-scale impacts of AI systems, and recognition that existing regulations and norms in industry and academia are insufficient to ensure responsible AI development.
Computers and Society
Multi-modal Self-Supervision from Generalized Data Transformations
In this paper, we show that, for videos, the answer is more complex, and that better results can be obtained by accounting for the interplay between invariance, distinctiveness, multiple modalities and time.
ELUDE: Generating interpretable explanations via a decomposition into labelled and unlabelled features
Specifically, we develop a novel explanation framework ELUDE (Explanation via Labelled and Unlabelled DEcomposition) that decomposes a model's prediction into two parts: one that is explainable through a linear combination of the semantic attributes, and another that is dependent on the set of uninterpretable features.
Gender Artifacts in Visual Datasets
Gender biases are known to exist within large-scale visual datasets and can be reflected or even amplified in downstream models.
"Help Me Help the AI": Understanding How Explainability Can Support Human-AI Interaction
Despite the proliferation of explainable AI (XAI) methods, little is understood about end-users' explainability needs and behaviors around XAI explanations.
Improving Data-Efficient Fossil Segmentation via Model Editing
Using a Mask R-CNN to segment ancient reef fossils in rock sample images, we present a two-part paradigm to improve fossil segmentation with few labeled images: we first identify model weaknesses using image perturbations and then mitigate those weaknesses using model editing.
UFO: A unified method for controlling Understandability and Faithfulness Objectives in concept-based explanations for CNNs
In this work, we propose UFO, a unified method for controlling Understandability and Faithfulness Objectives in concept-based explanations.
Humans, AI, and Context: Understanding End-Users' Trust in a Real-World Computer Vision Application
Trust is an important factor in people's interactions with AI systems.
