Explaining Deep Face Algorithms through Visualization: A Survey
- URL: http://arxiv.org/abs/2309.14715v1
- Date: Tue, 26 Sep 2023 07:16:39 GMT
- Title: Explaining Deep Face Algorithms through Visualization: A Survey
- Authors: Thrupthi Ann John, Vineeth N Balasubramanian, C. V. Jawahar
- Abstract summary: This work undertakes a first-of-its-kind meta-analysis of explainability algorithms in the face domain.
We review existing face explainability works and reveal valuable insights into the structure and hierarchy of face networks.
- Score: 57.60696799018538
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Although current deep models for face tasks surpass human performance on some
benchmarks, we do not understand how they work. Thus, we cannot predict how it
will react to novel inputs, resulting in catastrophic failures and unwanted
biases in the algorithms. Explainable AI helps bridge the gap, but currently,
there are very few visualization algorithms designed for faces. This work
undertakes a first-of-its-kind meta-analysis of explainability algorithms in
the face domain. We explore the nuances and caveats of adapting general-purpose
visualization algorithms to the face domain, illustrated by computing
visualizations on popular face models. We review existing face explainability
works and reveal valuable insights into the structure and hierarchy of face
networks. We also determine the design considerations for practical face
visualizations accessible to AI practitioners by conducting a user study on the
utility of various explainability algorithms.
Related papers
- Fiper: a Visual-based Explanation Combining Rules and Feature Importance [3.2982707161882967]
Explainable Artificial Intelligence aims to design tools and techniques to illustrate the predictions of the so-called black-box algorithms.
This paper proposes a visual-based method to illustrate rules paired with feature importance.
arXiv Detail & Related papers (2024-04-25T09:15:54Z) - Bridging Human Concepts and Computer Vision for Explainable Face Verification [2.9602845959184454]
We present an approach to combine computer and human vision to increase the explanation's interpretability of a face verification algorithm.
In particular, we are inspired by the human perceptual process to understand how machines perceive face's human-semantic areas.
arXiv Detail & Related papers (2024-01-30T09:13:49Z) - SEVA: Leveraging sketches to evaluate alignment between human and
machine visual abstraction [19.70530050403922]
Sketching is a powerful tool for creating abstract images that are sparse but meaningful.
Current vision algorithms have achieved high performance on a variety of visual tasks.
It remains unclear to what extent they understand sketches in a human-like way.
arXiv Detail & Related papers (2023-12-05T13:54:55Z) - Discriminative Deep Feature Visualization for Explainable Face
Recognition [9.105950041800225]
This paper contributes to the problem of explainable face recognition by first conceiving a face reconstruction-based explanation module.
To further interpret the decision of an FR model, a novel visual saliency explanation algorithm has been proposed.
arXiv Detail & Related papers (2023-06-01T07:06:43Z) - Eight Years of Face Recognition Research: Reproducibility, Achievements
and Open Issues [6.608320705848282]
Many different face recognition algorithms have been proposed in the last thirty years of intensive research in the field.
From the year 2015, state-of-the-art face recognition has been rooted in deep learning models.
This work is a followup from our previous works developed in 2014 and eventually published in 2016, showing the impact of various facial aspects on face recognition algorithms.
arXiv Detail & Related papers (2022-08-08T10:40:29Z) - Deep Learning-based Face Super-resolution: A Survey [78.11274281686246]
Face super-resolution, also known as face hallucination, is a domain-specific image super-resolution problem.
To date, few summaries of the studies on the deep learning-based face super-resolution are available.
In this survey, we present a comprehensive review of deep learning techniques in face super-resolution in a systematic manner.
arXiv Detail & Related papers (2021-01-11T08:17:11Z) - Facial Expressions as a Vulnerability in Face Recognition [73.85525896663371]
This work explores facial expression bias as a security vulnerability of face recognition systems.
We present a comprehensive analysis of how facial expression bias impacts the performance of face recognition technologies.
arXiv Detail & Related papers (2020-11-17T18:12:41Z) - Black-Box Face Recovery from Identity Features [61.950765357647605]
We attack the state-of-the-art face recognition system (ArcFace) to test our algorithm.
Our algorithm requires a significantly less number of queries compared to the state-of-the-art solution.
arXiv Detail & Related papers (2020-07-27T15:25:38Z) - On the Robustness of Face Recognition Algorithms Against Attacks and
Bias [78.68458616687634]
Face recognition algorithms have demonstrated very high recognition performance, suggesting suitability for real world applications.
Despite the enhanced accuracies, robustness of these algorithms against attacks and bias has been challenged.
This paper summarizes different ways in which the robustness of a face recognition algorithm is challenged.
arXiv Detail & Related papers (2020-02-07T18:21:59Z) - Exploiting Semantics for Face Image Deblurring [121.44928934662063]
We propose an effective and efficient face deblurring algorithm by exploiting semantic cues via deep convolutional neural networks.
We incorporate face semantic labels as input priors and propose an adaptive structural loss to regularize facial local structures.
The proposed method restores sharp images with more accurate facial features and details.
arXiv Detail & Related papers (2020-01-19T13:06:27Z)
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.