FGVC Workshop

We are not missing out! FGVC12 is excited to support "FOMO25: Foundation Model Challenge for Brain MRI".
This MICCAI25 challenge is still running and there is still time to participate!

Submission deadline: August 20, 2025
Join here: fomo25.github.io
Check out the thread below👇

Congratulations to the winners of the FGVC12 Best Paper Awards. 🎉
The best 4-page paper goes to Yiwen Liu et al. and the best 8-page paper to Darshana Saravanan et al..

We thank all authors for their contributions and especially our reviewers for their great support!!

We will be presenting the 🍄 FungiTastic 🍄, a multimodal, highly challenging dataset and benchmark covering many ML problems at @fgvcworkshop.bsky.social CVPR-W on Wednesday!

⏱️ 16:15
📍104 E, Level 1
📸 www.kaggle.com/datasets/pic...
📃 arxiv.org/abs/2408.13632

@cvprconference.bsky.social

Please join us for the FGVC workshop at CVPR 2025 @cvprconference.bsky.social on Wed 11th of June. The full schedule and list of fantastic speakers can be found on our website:
sites.google.com/view/fgvc12

Attending #CVPR2025? Take a moment to review our code of conduct.

Check out the CVPR Workshop proceeding papers presented at FGVC12:
openaccess.thecvf.com/CVPR2025_wor...

Poster session:
June 11, 4pm-6pm
ExHall D, poster boards 373-403

#CVPR25 @cvprconference.bsky.social

Come join us for the 12th Workshop on Fine-Grained Visual Categorization (FGVC). Starting today at 9am at @cvprconference.bsky.social.

We will be in room 104E.

#FGVC #CVPR2025
@fgvcworkshop.bsky.social

Check out the CVPR Workshop proceeding papers presented at FGVC12:
openaccess.thecvf.com/CVPR2025_wor...

Poster session:
June 11, 4pm-6pm
ExHall D, poster boards 373-403

#CVPR25 @cvprconference.bsky.social

#CVPR2025 Open Access Workshop Papers

openaccess.thecvf.com/CVPR2025_wor...

We are so excited to have this amazing line-up of speakers!!
Randall Balestriero, Kai Han, Mia Chiquier, Kenneth Marino (@kennethmarino.bsky.social‬), Elisa Ricci, Thomas Fel (@thomasfel.bsky.social‬)

Join us on June 11, 9am to discuss all things fine-grained!
We are looking forward to a series of talks on semantic granularity, covering topics such as machine teaching, interpretability and much more!
Room 104 E
Schedule & details: sites.google.com/view/fgvc12
@cvprconference.bsky.social #CVPR25

Are you a computer vision expert looking for a challenge?? Help us identify marine life! 🦑🧪🌊 Thank you @fgvcworkshop.bsky.social @kaggle.com for the support!!

FOMO25 accepted at #MICCAI2025! 🚀

Excited to announce the first challenge at MICCAI focusing on the development of self-supervised pretraining of foundation models for brain MRI! 🧠

With access to a large-scale dataset, codebase, cash prices and multiple tracks.

Read more ⬇️

The challenge is to classify volumetric µCT images of foraminifera tests. With only 210 labeled out of 18,426 volumes, the goal is to develop an efficient species classification method that minimizes annotation time, leveraging semi-supervised learning.
[5/5]

With µCT scanning, we can scan thousands of forams in a single scan. By determining the species composition, we can efficiently understand how the environment has evolved.
[4/5]

Since certain types of foraminifera only live in specific conditions, identifying the composition of the foraminifera sediments allows us to gain insights into past environmental conditions.
[3/5]

Planktonic foraminifera (aka forams) are tiny organisms that inhabit the sea waters. Forams produce a unique calcium carbonate shell, called a test, which can consist of multiple chambers and exhibit elaborate structures. These are preserved in sea sediments for millions of years.
[2/5]

Foram2025: Classifying microfossil volumes – the first step to understanding past climates.
👉 www.kaggle.com/competitions...
@cvprconference.bsky.social @kaggle.com
#FGVC #CVPR #CVPR2025 QIM Center (qim.dk)
[1/5]

This competition aims to identify under-studied species based on their acoustic signatures from continuous audio data. The most effective solutions will demonstrate the ability to train reliable classifiers with limited labeled data.
[4/4]

Conducting traditional surveys across large areas is costly. In contrast, passive acoustic monitoring, combined with modern ML techniques, enables conservationists to scale with greater temporal resolution, providing deeper insights into the effectiveness of restoration interventions.
[3/4]

Mobile and habitat-diverse species serve as valuable indicators of biodiversity change, as shifts in their assemblages and population dynamics can signal the success or failure of ecological restoration efforts.
[2/4]

BirdCLEF25: Audio-based species identification focused on birds, amphibians, mammals, and insects in Colombia.
👉 www.kaggle.com/competitions...
@cvprconference.bsky.social @kaggle.com
#FGVC #CVPR #CVPR2025 #LifeCLEF
[1/4]

For this competition the dataset contains 79 categories of marine animals of varying taxonomic ranks (e.g., family, genus, species). The challenge is to develop a model that can accurately classify these taxa and ideally leverage their taxonomic information to do so.
[5/5]

In marine ecology, accurate taxonomic classification is essential for addressing fundamental questions:
--> What species exist in a particular place?
--> What is the ecosystem biodiversity and how does it change over time?
[4/5]

Is that an Octopus rubescens, commonly found in this area, or is it an Octopus cyanea usually only observed in warm, tropical waters near Hawai’i? Accurate species classification is essential for understanding ocean ecosystems.
[3/5]

Consider marine wildlife monitoring in coastal waters near California. Daily video footage analyzed by a standard ML model shows 2 octopuses, 1 shark, and 10 jellyfish - broad taxonomic categories. But species-level identification could reveal crucial details.
[2/5]

FathomNet25: Navigating the Depths: Advancing Hierarchical Classification of Ocean Life
www.kaggle.com/competitions...
@fathomnet.bsky.social @fathomverse.bsky.social @mbarinews.bsky.social
@cvprconference.bsky.social @kaggle.com
#FGVC #CVPR #CVPR2025
[1/5]

This challenge is about individual animal identification of loggerhead sea turtles, salamanders, and Eurasian lynxes. Your goal will be to design a model that, for each image, determines whether the depicted animal is new (not present in the training dataset) or known (to be classified).
[4/4]

But there’s a catch: many current models overfit to the background instead of the animal’s unique features. That means they often fail in new environments. Hence, we need models that generalize better across diverse habitats and allow us to identify novel specimen.
[3/4]

Identifying individual animals is key to understanding wildlife populations, movements, and behaviors. By automating this process using AI, researchers can gather powerful data to track migration, monitor ecosystems, and shape smarter conservation strategies.
[2/4]