Nico Lang @nicolangnl

Postdoc @AiCentreDK & @DIKU_Institut | #ComputerVision #MachineLearning #RemoteSensing for environmental science. | PhD from @eth_en | https://t.co/9Zv5cR2qI0 langnico.github.io Copenhagen Joined February 2017

Tweets

444
Followers

1K
Following

1K
Likes

2K

FGVC Workshop @fgvcworkshop

5 months ago

Foram2025: Classifying microfossil volumes – the first step to understanding past climates. 👉 kaggle.com/competitions/f… @CVPR @kaggle #FGVC #CVPR #CVPR2025 @QIMCenter [1/5]

1 2 3 2K 0

Download Image

FGVC Workshop @fgvcworkshop

5 months ago

FathomNet25: Navigating the Depths: Advancing Hierarchical Classification of Ocean Life kaggle.com/competitions/f… @FathomNet @CVPR @kaggle #FGVC #CVPR #CVPR2025 [1/5]

1 2 3 2K 0

Download Image

FGVC Workshop @fgvcworkshop

5 months ago

GeoLifeCLEF25: Location-based species presence prediction 👉 kaggle.com/competitions/g… @CVPR @kaggle @LifeCLEF #FGVC #CVPR #CVPR2025 [1/3]

1 3 3 2K 1

Download Image

FGVC Workshop @fgvcworkshop

5 months ago

PlantCLEF25: Multi-species plant identification in vegetation quadrat images 👉 kaggle.com/competitions/p… @cvprconference @kaggle #FGVC #CVPR #CVPR2025 @LifeCLEF [1/4]

1 5 8 2K 0

Download Image

FGVC Workshop @fgvcworkshop

5 months ago

Looking for a challenge? Along with FGVC12 at #CVPR2025, multiple fine-grained computer vision competitions have been launched. These well-curated datasets allow you to leverage your AI skills to boost applications with impact! Let's go: sites.google.com/view/fgvc12/co… @CVPR @kaggle

2 4 23 4K 5

Download Image

FGVC Workshop @fgvcworkshop

5 months ago

@CVPR @kaggle FungiCLEF25: Few-shot classification with rare fungi species 👉 kaggle.com/competitions/f… @CVPR @kaggle #FGVC #CVPR #CVPR2025 #LifeCLEF [1/2]

1 2 4 536 0

Download Image

Nico Lang @nicolangnl

5 months ago

There is approx. 2 months time to join these competitions co-hosted by @fgvcworkshop at #CVPR2025. Our collaborators put together an interesting suite of problems in applications that have great potential for positive impact. You can start here: sites.google.com/view/fgvc12/co…

FGVC Workshop @fgvcworkshop

5 months ago

2 4 23 4K 5

Download Image

0 2 11 1K 4

FGVC Workshop @fgvcworkshop

5 months ago

We extended the deadline for Non-archival submissions to *April 02*. More infos on the call for papers and the link to the CMT portal can be found here: sites.google.com/view/fgvc12/su… @CVPR #CVPR #CVPR2025 #AI

FGVC Workshop @fgvcworkshop

8 months ago

1 9 8 5K 0

Download Image

0 4 5 941 0

FGVC Workshop @fgvcworkshop

6 months ago

Submission deadline is extended to **March 07**. The CMT page is now online and we are looking forward to your submissions on AI systems for expert-tasks and fine-grained analysis. More info at: sites.google.com/view/fgvc12/su… @CVPR #CVPR #CVPR2025 #AI

FGVC Workshop @fgvcworkshop

8 months ago

1 9 8 5K 0

Download Image

3 4 5 947 0

Nico Lang @nicolangnl

8 months ago

FGVC12 Workshop is coming to #CVPR2025 in Nashville! Are you working on fine-grained visual problems? This year we have two peer-reviewed paper tracks: i) 8-page CVPR Workshop proceedings ii) 4-page non-archival extended abstracts CALL FOR PAPERS: sites.google.com/view/fgvc12/su… @CVPR

FGVC Workshop @fgvcworkshop

8 months ago

1 9 8 5K 0

Download Image

0 0 4 345 0

Eddie Vendrow @EdwardVendrow

9 months ago

🎯 How can we empower scientific discovery in millions of nature photos? Introducing INQUIRE: A benchmark testing if AI vision-language models can help scientists find biodiversity patterns- from disease symptoms to rare behaviors- hidden in vast image collections. Thread👇🧵

1 10 31 20K 5

Download Image

Oisin Mac Aodha @oisinmacaodha

11 months ago

Come visit our poster (number 23) this afternoon at #ECCV2024 to learn more. You can also find the paper online here: Labeled Data Selection for Category Discovery arxiv.org/abs/2406.04898

1 3 8 607 0

Oisin Mac Aodha @oisinmacaodha

11 months ago

We discovered an interesting observation that the best labelled data to use should not be too similar, nor too dissimilar, to the unlabelled data. Taking this into account results in large improvements across a range of GCD methods.

1 1 2 282 0

Download Image

Oisin Mac Aodha @oisinmacaodha

11 months ago

Some questions that arise from this include: (i) What is the impact of choosing different labelled datasets to train my model? (ii) How can I choose the best labelled set for my problem?

1 1 2 204 0

Oisin Mac Aodha @oisinmacaodha

11 months ago

In Generalized Category Discovery (GCD), the goal is to train models that can discover new categories using knowledge learned from a labelled dataset.