Thomas Fel
Hi đź‘‹
I am Thomas Fel, a 2nd year French PhD student (2021 - 2024) student supervised by
Thomas Serre At
ANITI (Toulouse, France)
& Brown University (Boston, USA).
I am also part of the incredible
DEEL
core team.
I'm interested in Explainability (XAI), computer vision, optimization and certification of
neural network systems.
Most of my research involves reverse engineering existing neural networks to understand their
critical strategies.
In my free time I also like to contribute to open source project
in particular, I am the author of Xplique .
thomas_fel@brown.edu  / 
Google Scholar
 / 
Twitter  / 
Github
NEWS
- 09/2022 : 3 papers accepted at NeurIPS!
- 07/2022 : Oral presentation of 'Don't lie to me' at ICML Workshop
- 06/2022 : Presentation of Xplique at CVPR
- 12/2021 : 'How Good is your Explanation?' accepted at WACV 2022!
- 09/2021 : Sobol Attribution Method accepted at NeurIPS!
- 04/2021 : Official start of the thesis
|
|
|
CRAFT: Concept Recursive Activation FacTorization
Thomas Fel*, Agustin Picard*, Louis Béthune*, Thibaut Boissin*,
David Vigouroux, Julien Colin, Rémi Cadène, Thomas Serre
Under review, 2022
Despite their considerable potential, concept-based explainability methods have received relatively
little attention,
and explaining what’s driving models’ decisions and where it’s located in the input is still an open
problem.
To tackle this, we revisit unsupervised concept extraction techniques for explaining the decisions
of deep neural networks and present CRAFT
– a framework to generate concept-based explanations for understanding individual predictions and
the model’s high-level logic for whole classes.
CRAFT takes advantage of a novel method for recursively decomposing higher-level concepts into more
elementary ones, combined with a
novel approach for better estimating the importance of identified concepts with Sobol indices.
Furthermore, we show how implicit differentiation can be used to generate concept-wise attribution
explanations for individual images.
We further demonstrate through fidelity metrics that our proposed concept importance estimation
technique is more faithful to the model than previous methods,
and, through human psychophysic experiments, we confirm that our recursive decomposition can
generate meaningful and accurate concepts.
Finally, we illustrate CRAFT’s potential to enable the understanding of predictions of trained
models on multiple use-cases by
producing meaningful concept-based explanations.
|
|
Harmonizing the object recognition strategies of deep neural networks with humans
Thomas Fel*, Ivan Felipe*, Drew Linsley*, Thomas Serre
NeurIPS Proceedings of the Conference on Neural
Information Processing Systems, 2022
The many successes of deep neural networks (DNNs) over the past decade have largely been driven by
computational scale rather than insights from biological intelligence.
Here, we explore if these trends have also carried concomitant improvements in explaining the visual
strategies humans rely on for object recognition.
We do this by comparing two related but distinct properties of visual strategies in humans and DNNs:
where they believe important visual features are in images and how they use those features to
categorize objects.
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.
State-of-the-art DNNs are progressively becoming less aligned with humans as their accuracy
improves.
We rectify this growing issue with our harmonization loss: a general-purpose training routine that
both aligns DNN and human visual strategies and improves categorization accuracy.
Our work represents the first demonstration that the scaling laws that are guiding the design of
DNNs today have also produced worse models of human vision.
|
|
What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability
Methods
Julien Colin*, Thomas Fel*, Rémi Cadène, Thomas Serre.
NeurIPS Proceedings of the Conference on Neural
Information Processing Systems, 2022
In this work, we conducted psychophysics experiments at scale to evaluate the ability of human
participants to
leverage representative attribution methods for understanding the behavior of different image
classifiers representing
three real-world scenarios: (1) identifying bias, (2) characterizing novel strategy and (3)
understanding failure cases.
Our results demonstrate that the degree to which individual attribution methods help human
participants better
understand an AI system varied widely across these scenarios.
This suggests a critical need for the field to move past quantitative improvements of current
attribution methods.
|
|
Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure
Paul Novello, Thomas Fel, David Vigouroux
NeurIPS Proceedings of the Conference on Neural
Information Processing Systems, 2022
This paper could be seen as a follow-up to Look at the variance and further improves the efficiency
of black-box
methods using Hilbert-Schmidt Independence Criterion (HSIC).
HSIC measures the dependence between regions of an input image and the output of a model based
on kernel embeddings of distributions.
Our experiments show that HSIC is up to 8 times faster than the previous best black-box attribution
methods
while being as faithful.
Importantly, we show that these advances can be transposed to efficiently and faithfully explain
object detection
models such as YOLOv4.
|
|
Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysis
Thomas Fel*, Melanie Ducoffe*, David Vigouroux, Remi Cadene,
Mikael Capelle, Claire Nicodeme, Thomas Serre
ICML Workshop on Formal Verification of Machine
Learning (Oral), 2022
In this work, we propose the first explainability method based on formal method and therefore able
to meet certification requirements.
Specifically, we introduce EVA (Explaining using Verified perturbation Analysis)
-- the first explainability method guarantee to have an exhaustive exploration of a perturbation
space.
We leverage the beneficial properties of verified perturbation analysis -- time efficiency,
tractability
and guaranteed complete coverage of a manifold -- to efficiently characterize the input variables
that are most
likely to drive the model decision.
We evaluate the approach systematically and demonstrate state-of-the-art results on multiple
benchmarks.
|
|
When adversarial attacks become interpretable counterfactual explanations
Mathieu Serrurier, Franck Mamalet, Thomas Fel, Louis Béthune, Thibaut Boissin
Under review, 2022
We argue that, when learning a 1-Lipschitz neural network with the dual loss of an
optimal transportation problem, the gradient of the model is both the direction of
the transportation plan and the direction to the closest adversarial attack. Traveling
along the gradient to the decision boundary is no more an adversarial attack but
becomes a counterfactual explanation, explicitly transporting from one class to
the other. Through extensive experiments on XAI metrics, we find that the simple
saliency map method, applied on such networks, becomes a reliable explanation!
The proposed networks were already known to be certifiably robust, and
we prove that they are also tailored for explainability.
|
|
Xplique: A Deep Learning Explainability Toolbox
Thomas Fel*, Lucas Hervier*, David Vigouroux, Antonin Poche, Justin Plakoo,
Remi Cadene, Mathieu Chalvidal, Julien Colin, Thibaut Boissin, Louis Bethune, Agustin Picard, Claire
Nicodeme,
Laurent Gardes, Gregory Flandin, Thomas Serre
CVPR Workshop on Explainable Artificial
Intelligence for Computer Vision, 2022
For more than a year, I worked alongside my thesis to implement more than fifty explainability
papers.
Xplique is the result of this work, it is a library that I develop and maintain.
The library is composed of several modules:
(1) the Attributions Methods module,
(2) The Feature Visualization module,
(3) The Concepts module and
(4) the Metrics module.
|
|
Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis
Thomas Fel*,
Rémi Cadène*, Mathieu Chalvidal, Matthieu Cord, David Vigouroux, Thomas Serre.
NeurIPSProceedings of the Conference on Neural
Information
Processing Systems, 2021
We describe a novel and efficient black-box attribution method which is grounded in Sensitivity
Analysis and uses Sobol indices.
Beyond modeling the individual contributions of image regions, Sobol indices provide an efficient
way to capture
higher-order interactions between image regions and their contributions to a neural network's
prediction through
the lens of variance.
|
|
How Good is your Explanation? Algorithmic Stability Measures to Assess the
Quality of Explanations for Deep Neural Networks
Thomas Fel,
David Vigouroux, Rémi Cadène, Thomas Serre.
WACVProceedings of the IEEE/CVF Winter Conference
on
Applications of Computer Vision, 2022
We propose two new measures to evaluate explanations borrowed from the field of algorithmic
stability:
mean generalizability MeGe and relative consistency ReCo. We conduct extensive experiments on
different network
architectures, common explainability methods, and several image datasets to demonstrate the benefits
of
the proposed metrics and show that popular fidelity measures are not sufficient to guarantee
trustworthy explanations.
Finally, we found that 1-Lipschitz networks produce explanations with higher MeGe and ReCo than
common neural networks.
|
|