Workshop on Synthetic Data for Computer Vision (SyntheticData4CV 2024) Call for Papers

Call for Papers

Workshop on Synthetic Data for Computer Vision  (SyntheticData4CV 2024)

https://syntheticdata4cv.wordpress.com/

to be held as part of the 
18th European Conference on Computer Vision (ECCV 2024)

-----------------------------------------------------
Important Dates
-----------------------------------------------------

Submission Deadline: July 10, 2024

Notification of Acceptance: August 7, 2024

Camera Ready Deadline: August 25, 2024

Workshop: Sept 29 or Sept 30, 2024 (to be defined) - Milan, Italy


------------------------------------------------------
Workshop Aims and Scope
------------------------------------------------------

In the dynamic landscape of computer vision, synthetic data is
emerging as a key resource to overcome data limitations and improve
the accuracy and reliability of systems. Advanced generative models
like diffusion models, GANs, and multimodal models can generate large
amounts of data with different characteristics to address data
insufficiency and bias, as well as privacy concerns, by removing
sensitive information or generating data without it.

These advances are particularly significant in several areas, such as
healthcare, where privacy and data protection laws limit access to
real patient data. In addition, simulating rare medical disorders
could improve model accuracy and generalizability. Furthermore, these
data present a compelling opportunity for resource optimization by
removing the need to store massive datasets; they can be generated and
dynamically provided to learning models during training. This workshop
aims to explore not only the favorable impacts of synthetic data, such
as those just delineated, but also the challenges and risks associated
with their potential misuse. Particularly in the area of security,
synthetic data could be exploited to circumvent biometric recognition
systems, undermining their effectiveness and enabling unauthorized
access or fraudulent activities. Therefore, there is an imperative not
only to generate increasingly high-quality data but also to develop
robust algorithms for their detection.


--------------------------------------------------------
Workshop Keywords
--------------------------------------------------------

Image Synthesis; Responsible Synthetic Data Use; Computer Vision;
Synthetic Biometrics; Synthetic dataset; Medical image synthesis

-------------------------------------------------------

Workshop Topics
-------------------------------------------------------

The workshop welcomes contributions on all topics related to synthetic
data in the field of computer vision, focused (but not limited to):


Responsible Image Synthesis:

    Fairness & Robustness: For example, collecting and preparing
    synthetic datasets that fairly represent different classes;
    simulating the most difficult and rare conditions to improve the
    robustness and generalizability of systems.

    Bias & Ethics: For instance, implementing validation procedures to
    ensure that synthetic datasets do not contain unintentional bias;
    setting clear ethical guidelines to prevent the misuse of that
    data.

    Privacy & Security: Examples include anonymization and
    de-identification to prevent data linking to real people; using
    synthetic data to enhance communication rounds in federated
    learning.

    Reliability: Conducting experiments to test reliability and
    accuracy in various application contexts by comparing the results
    achieved using synthetic information with those obtained using
    real data; enabling a deeper understanding of the algorithms and
    decisions made in the generation process.


Generative Models:

    Stable Diffusion Models: Such as personalization, conditional
    generation, guidance, and controllability; innovative approaches
    for training or architectures.

    3D Models: Overcoming challenges related to shape diversity,
    structure, and object complexity; exploring how they can be
    integrated into VR and AR applications.

    Deepfakes: Developing algorithms and systems to identify and
    neutralize deepfake content to prevent misinformation and protect
    individual identities; forensic techniques for analysis and
    attribution of deepfake videos.


Learning from Synthetic Data:

    Frameworks: Domain generalization by training models on a wide
    array of simulated conditions; addressing the domain adaptation
    challenge, and assessing the effectiveness of transfer learning
    techniques.

    Strategies: Continual learning by generating dynamic datasets that
    reflect evolving conditions and novel challenges; one- or few-shot
    learning by generating diverse and comprehensive datasets from a
    limited number of real-world examples.

    Theoretical Foundations: Development of benchmarks and validation
    protocols to evaluate the effectiveness of models trained on
    synthetic data; establishing standardized tests to ensure
    reliability and robustness across various synthetic datasets.


Applications:

    Medical Image Synthesis:

    Generation of Synthetic Diagnostic Images: Improving the realism,
    diversity, and clinical relevance of synthetic medical images to
    aid in training and evaluating diagnostic systems; ethical
    implications of using synthetic data in healthcare: patient
    privacy concerns, and strategies to mitigate potential risks.

    Simulation of Pathological Variants for Medical Model Training:
    Incorporating expert knowledge into a machine learning model to
    define a fine-tuning objective; techniques for tailoring synthetic
    images conditioned on clinical concepts.

    Synthetic Data for Disease Progression Modeling: Frameworks that
    capture the temporal evolution of diseases; simulations of the
    impact of potential treatments and interventions, providing a
    controlled environment for testing novel medical strategies.

    Synthetic Biometrics:

        Innovative Synthesis of Biometric Data: Development of
        advanced techniques for synthetic biometric generation;
        identification of core technical challenges.

        Label Generation: Implementation of automatic annotation
        techniques; ensuring label accuracy and consistency.

        Quality Assessment: Methods to evaluate synthetic biometric
        data quality and realism; comparison tools and metrics against
        real data.

    Others.



-------------------------------------------------------
Submission Details
-------------------------------------------------------


Format and paper length


All submissions must be presented in English. Authors are encouraged
to refer to the ECCV 2024 Suggested Practices for Authors and utilize
the official proceedings templates provided for either LaTeX or Word
formats.

We invite participants to submit their contributions to the workshop
in the form of full papers. These submissions may extend up to 14
pages, inclusive of figures and tables, formatted according to the
Springer LNCS style. Additional pages dedicated solely to cited
references are permissible.



Submission policy


Submissions must contain original research that has not been
previously published. Authors are encouraged to adhere to the ECCV
paper preparation guidelines. All papers must be submitted
electronically through the CMT system.


Double-Blind Review Policy

Submissions will undergo a double-blind review process. To ensure anonymity:

    Remove all identifying information, including author names and institutional affiliations, from the title and header areas of the paper.

    Omit acknowledgments.

    Maintain citations to your own previous work unanonymized to allow
    reviewers to assess all relevant research, but refer to your work
    in the third person (e.g., "[22] found that...").

Papers that are not properly anonymized, do not follow the provided
template, or fail to comply with these guidelines will be rejected
without review. During the review, authors can address the reviewers'
comments in a rebuttal period before a final decision is made. Each
submission will be reviewed by at least three members of the Program
Committee. Authors are encouraged to make their code and data
available anonymously (e.g., through an anonymous GitHub
repository). Supplementary materials like images, videos, appendices,
and technical reports can optionally be included, but must also be
anonymized.


Proceedings

Accepted papers will be published as part of the official ECCV 2024
workshop proceedings. Furthermore, the best papers will be invited to
submit an extended version to the Elsevier Image and Vision Computing
Journal, which has an impact factor of 4.7. This opportunity allows
for additional visibility and an extended presentation of their
work. These extended manuscripts will undergo another peer-review
process. The authors must submit an extended version of the accepted
paper with at least 30 or 40% new and original content.



Author Guidelines for Workshop Participation

Papers not selected for oral presentation will be presented in a
poster session. We expect each paper to be presented in-person by an
author (or an authorized delegate).

Note: To ensure publication of the paper in the ECCV 2024 proceedings
of Springer at least one author must register for the conference.

--------------------------------------------------------
Workshop Organizers
---------------------------------------------------------

Lucia Cascone
University of Salerno, Fisciano, Italy
Email: lcascone@unisa.it

Zilong Huang

Tencent, China

Email: zilong.huang2020@gmail.com


Michele Nappi
University of Salerno, Fisciano, Italy
Email: mnappi@unisa.it

Xinggang Wang

Huazhong University of Science and Technology, China
Email: xgwang@hust.edu.cn

-----------------------------------------------------------
Contacts
-----------------------------------------------------------

For general inquiries regarding the workshop, please direct your
emails to: syntheticdata4cv@gmail.com