OVERVIEW

FGVC7: The Seventh Workshop on Fine-Grained Visual Categorization

June 19th in conjunction with CVPR 2020, June, Seattle, USA.

Website: https://sites.google.com/view/fgvc7

Twitter: @fgvcworkshop


The purpose of this workshop is to bring together researchers to explore visual recognition across the continuum between basic level categorization (object recognition) and identification of individuals (face recognition, biometrics) within a category population. Participants are encouraged to submit short papers relevant to the workshop and to take part in a set of competitions organized in conjunction with the workshop - details below.



WORKSHOP DESCRIPTION

Fine-grained categorization (called `subordinate categorization’ in the psychology literature) lies in the continuum between basic-level categorization (object recognition) and the identification of individuals (e.g., face recognition, biometrics). The visual distinctions between similar categories are often quite subtle and therefore difficult to address with today’s general-purpose object recognition machinery. This is especially true for domains where data is not readily available on the web (e.g., medical images, or depth data), or domains for which training data is limited. It is likely that a radical re-thinking of the techniques used for representation learning, architecture design, human-in-the-loop learning, few-shot, and self-supervised learning that are currently used for visual recognition will be needed to improve fine-grained categorization.

It is our hope that the invited talks, including researchers from scientific application domains, will shed light on human expertise and human performance in subordinate categorization and on motivating research applications. More information about previous FGVC workshops and competitions can be found at http://www.fgvc.org/.


PAPER SUBMISSION

We invite submission of 3 page (excluding references) extended abstracts (using the CVPR 2020 format) describing work in the domains suggested above or in closely-related areas. Accepted submissions will be presented as posters at the workshop. Reviewing of abstract submissions will be double-blind. The purpose of this workshop is not as a venue for publication, so much as a place to gather together those in the community working on or interested in FGVC. Submissions of work which has been previously published, including papers accepted to the main CVPR 2020 conference are allowed.


For more details see - https://sites.google.com/view/fgvc7/submission



Topics of interest include the following:



Fine-grained categorization

* Novel datasets and data collection strategies for fine-grained categorization

* Appropriate error metrics for fine-grained categorization

* Low/few shot learning

* Self-supervised learning

* Transfer-learning from known to novel subcategories

* Attribute and part based approaches

* Taxonomic predictions


Human-in-the-loop

* Fine-grained categorization with humans in the loop

* Embedding human experts’ knowledge into computational models

* Machine teaching

* Interpretable fine-grained models


Multimodal learning

* Using audio and video data

* Using geographical priors

* Using shape/3D information


Fine-grained applications

* Product recognition

* Animal biometrics and camera traps

* Museum collections e.g. biological, art, ...



PAPER SUBMISSION DATES

* Submission Deadline: 27th March 2020

* Decisions: 27th April 2020

* Camera Ready Deadline: 7th May 2020

* Submission site: CMT URL will be available on our site soon https://sites.google.com/view/fgvc7/submission



COMPETITIONS

We will be holding six fine-grained computer vision challenges with tasks ranging from classification of attributes in art images through to classifying diseases in plants. The competitions are hosted on Kaggle.


For more details please visit:

FGVC https://sites.google.com/view/fgvc7



COMPETITION DATES

* Competitions start: March 2020

* Competitions end: May 2020



ORGANIZERS

Oisin Mac Aodha - University of Edinburgh

Ryan Farrell - Brigham Young University

Subhransu Maji - University of Massachusetts, Amherst

Christine Kaeser-Chen - Google

Grant Van Horn - Cornell Lab of Ornithology

Hartwig Adam - Google

Serge Belongie - Cornell University