Justin Kay
@justin-kay.bsky.social
PhD student at MIT. Machine learning, computer vision, ecology, climate. Previously: Co-founder, CTO Ai.Fish; Researcher at Caltech; UC Berkeley. justinkay.github.io
Pinned
Justin Kay
@justin-kay.bsky.social
· Oct 13
There are now millions of publicly-available AI models – which one is right for you?
We introduce CODA ( #ICCV2025 Highlight! ), a method for *active model selection.* CODA selects the best model for your data with any labeling budget – often as few as 25 labeled examples. 1/
@iccv.bsky.social
We introduce CODA ( #ICCV2025 Highlight! ), a method for *active model selection.* CODA selects the best model for your data with any labeling budget – often as few as 25 labeled examples. 1/
@iccv.bsky.social
Reposted by Justin Kay
From medicine to geo-guessing, humans can get incredibly good at solving visual recognition tasks.
But how is this skill learned, and can we model its progression?
We present CleverBirds, accepted #NeurIPS2025, a large-scale benchmark for visual knowledge tracing.
📄 arxiv.org/abs/2511.08512
1/5
But how is this skill learned, and can we model its progression?
We present CleverBirds, accepted #NeurIPS2025, a large-scale benchmark for visual knowledge tracing.
📄 arxiv.org/abs/2511.08512
1/5
CleverBirds: A Multiple-Choice Benchmark for Fine-grained Human Knowledge Tracing
Mastering fine-grained visual recognition, essential in many expert domains, can require that specialists undergo years of dedicated training. Modeling the progression of such expertize in humans rema...
arxiv.org
November 12, 2025 at 3:29 PM
From medicine to geo-guessing, humans can get incredibly good at solving visual recognition tasks.
But how is this skill learned, and can we model its progression?
We present CleverBirds, accepted #NeurIPS2025, a large-scale benchmark for visual knowledge tracing.
📄 arxiv.org/abs/2511.08512
1/5
But how is this skill learned, and can we model its progression?
We present CleverBirds, accepted #NeurIPS2025, a large-scale benchmark for visual knowledge tracing.
📄 arxiv.org/abs/2511.08512
1/5
Wrapping up @iccv.bsky.social with an in-person CODA demo session! Try it yourself here if you missed us: t.co/yUWp8UCg47
October 24, 2025 at 2:36 AM
Wrapping up @iccv.bsky.social with an in-person CODA demo session! Try it yourself here if you missed us: t.co/yUWp8UCg47
Reposted by Justin Kay
Are you coming to @iccv.bsky.social??
Do you like BIRDS?!?! The #CVBirdWalk is happening!!!
Oct. 21, 7am, Ala Moana Park. Kick off your conference right!!
#ICCV2025 #AIforConservation
Do you like BIRDS?!?! The #CVBirdWalk is happening!!!
Oct. 21, 7am, Ala Moana Park. Kick off your conference right!!
#ICCV2025 #AIforConservation
October 17, 2025 at 11:36 PM
Are you coming to @iccv.bsky.social??
Do you like BIRDS?!?! The #CVBirdWalk is happening!!!
Oct. 21, 7am, Ala Moana Park. Kick off your conference right!!
#ICCV2025 #AIforConservation
Do you like BIRDS?!?! The #CVBirdWalk is happening!!!
Oct. 21, 7am, Ala Moana Park. Kick off your conference right!!
#ICCV2025 #AIforConservation
Join us tomorrow for the Joint Workshop on Marine Vision at #ICCV2025 (@iccv.bsky.social), from 9-6 in Room 318B!
Check out the full program here: vap.aau.dk/marinevision/
Check out the full program here: vap.aau.dk/marinevision/
October 18, 2025 at 9:00 PM
Join us tomorrow for the Joint Workshop on Marine Vision at #ICCV2025 (@iccv.bsky.social), from 9-6 in Room 318B!
Check out the full program here: vap.aau.dk/marinevision/
Check out the full program here: vap.aau.dk/marinevision/
Reposted by Justin Kay
Interested in doing a PhD in machine learning at the University of Edinburgh starting Sept 2026?
My group works on topics in vision, machine learning, and AI for climate.
For more information and details on how to get in touch, please check out my website:
homepages.inf.ed.ac.uk/omacaod
My group works on topics in vision, machine learning, and AI for climate.
For more information and details on how to get in touch, please check out my website:
homepages.inf.ed.ac.uk/omacaod
October 16, 2025 at 9:15 AM
Interested in doing a PhD in machine learning at the University of Edinburgh starting Sept 2026?
My group works on topics in vision, machine learning, and AI for climate.
For more information and details on how to get in touch, please check out my website:
homepages.inf.ed.ac.uk/omacaod
My group works on topics in vision, machine learning, and AI for climate.
For more information and details on how to get in touch, please check out my website:
homepages.inf.ed.ac.uk/omacaod
Reposted by Justin Kay
This new work by @justin-kay.bsky.social provides ML users with an efficient mechanism to wade through the sea of available open-source models and identify which model will work best for their needs!
Check it out below, and learn more at our @iccv.bsky.social poster (highlight!) on 10/21!!
Check it out below, and learn more at our @iccv.bsky.social poster (highlight!) on 10/21!!
There are now millions of publicly-available AI models – which one is right for you?
We introduce CODA ( #ICCV2025 Highlight! ), a method for *active model selection.* CODA selects the best model for your data with any labeling budget – often as few as 25 labeled examples. 1/
@iccv.bsky.social
We introduce CODA ( #ICCV2025 Highlight! ), a method for *active model selection.* CODA selects the best model for your data with any labeling budget – often as few as 25 labeled examples. 1/
@iccv.bsky.social
October 13, 2025 at 7:13 PM
This new work by @justin-kay.bsky.social provides ML users with an efficient mechanism to wade through the sea of available open-source models and identify which model will work best for their needs!
Check it out below, and learn more at our @iccv.bsky.social poster (highlight!) on 10/21!!
Check it out below, and learn more at our @iccv.bsky.social poster (highlight!) on 10/21!!
There are now millions of publicly-available AI models – which one is right for you?
We introduce CODA ( #ICCV2025 Highlight! ), a method for *active model selection.* CODA selects the best model for your data with any labeling budget – often as few as 25 labeled examples. 1/
@iccv.bsky.social
We introduce CODA ( #ICCV2025 Highlight! ), a method for *active model selection.* CODA selects the best model for your data with any labeling budget – often as few as 25 labeled examples. 1/
@iccv.bsky.social
October 13, 2025 at 6:00 PM
There are now millions of publicly-available AI models – which one is right for you?
We introduce CODA ( #ICCV2025 Highlight! ), a method for *active model selection.* CODA selects the best model for your data with any labeling budget – often as few as 25 labeled examples. 1/
@iccv.bsky.social
We introduce CODA ( #ICCV2025 Highlight! ), a method for *active model selection.* CODA selects the best model for your data with any labeling budget – often as few as 25 labeled examples. 1/
@iccv.bsky.social
Reposted by Justin Kay
Join us at the Joint Workshop for Marine Vision at #ICCV25
We have full-paper and nectar tracks.
Accepted papers are included in the official ICCV workshop proceedings.
Submission deadline: June 30
More at: vap.aau.dk/marinevision/
@iccv.bsky.social
@jbhaurum.bsky.social
@justin-kay.bsky.social
We have full-paper and nectar tracks.
Accepted papers are included in the official ICCV workshop proceedings.
Submission deadline: June 30
More at: vap.aau.dk/marinevision/
@iccv.bsky.social
@jbhaurum.bsky.social
@justin-kay.bsky.social
June 3, 2025 at 7:27 AM
Join us at the Joint Workshop for Marine Vision at #ICCV25
We have full-paper and nectar tracks.
Accepted papers are included in the official ICCV workshop proceedings.
Submission deadline: June 30
More at: vap.aau.dk/marinevision/
@iccv.bsky.social
@jbhaurum.bsky.social
@justin-kay.bsky.social
We have full-paper and nectar tracks.
Accepted papers are included in the official ICCV workshop proceedings.
Submission deadline: June 30
More at: vap.aau.dk/marinevision/
@iccv.bsky.social
@jbhaurum.bsky.social
@justin-kay.bsky.social
Reposted by Justin Kay
The call for applications has just been released for #CV4Ecology2026!! This three-week intensive program trains ecologists and conservation practitioners to develop their own AI tools for their own data.
When: Jan 12-30, 2026
Where: SCBI @smconservation.bsky.social
When: Jan 12-30, 2026
Where: SCBI @smconservation.bsky.social
May 12, 2025 at 7:08 PM
The call for applications has just been released for #CV4Ecology2026!! This three-week intensive program trains ecologists and conservation practitioners to develop their own AI tools for their own data.
When: Jan 12-30, 2026
Where: SCBI @smconservation.bsky.social
When: Jan 12-30, 2026
Where: SCBI @smconservation.bsky.social
Reposted by Justin Kay
There will be a workshop on underwater computer vision at @iccv.bsky.social with papers included in the proceedings (approx. deadline ultimo June) - more information coming soon! @justin-kay.bsky.social @jbhaurum.bsky.social
@aicentre.dk
@aicentre.dk
May 4, 2025 at 6:21 PM
There will be a workshop on underwater computer vision at @iccv.bsky.social with papers included in the proceedings (approx. deadline ultimo June) - more information coming soon! @justin-kay.bsky.social @jbhaurum.bsky.social
@aicentre.dk
@aicentre.dk
Reposted by Justin Kay
A syllabus for a course on machine learning evaluation.
Machine Learning Evaluation - A Syllabus
What we read this semester, and what worked, and what didn't.
www.argmin.net
April 24, 2025 at 2:30 PM
A syllabus for a course on machine learning evaluation.
Reposted by Justin Kay
Have you ever wondered what makes two models different?
We all know the ViT-Large performs better than the Resnet-50, but what visual concepts drive this difference? Our new ICLR 2025 paper addresses this question! nkondapa.github.io/rsvc-page/
We all know the ViT-Large performs better than the Resnet-50, but what visual concepts drive this difference? Our new ICLR 2025 paper addresses this question! nkondapa.github.io/rsvc-page/
April 11, 2025 at 4:11 PM
Have you ever wondered what makes two models different?
We all know the ViT-Large performs better than the Resnet-50, but what visual concepts drive this difference? Our new ICLR 2025 paper addresses this question! nkondapa.github.io/rsvc-page/
We all know the ViT-Large performs better than the Resnet-50, but what visual concepts drive this difference? Our new ICLR 2025 paper addresses this question! nkondapa.github.io/rsvc-page/
Reposted by Justin Kay
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]
👉 www.kaggle.com/competitions...
@cvprconference.bsky.social @kaggle.com
#FGVC #CVPR #CVPR2025 #LifeCLEF
[1/4]
April 9, 2025 at 10:22 AM
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]
👉 www.kaggle.com/competitions...
@cvprconference.bsky.social @kaggle.com
#FGVC #CVPR #CVPR2025 #LifeCLEF
[1/4]
Adapt object detectors to new data *without labels* with Align and Distill (ALDI), our domain adaptation framework published last week in Transactions on Machine Learning Research (with a Featured Certification [Spotlight]!)
April 8, 2025 at 4:26 PM
Adapt object detectors to new data *without labels* with Align and Distill (ALDI), our domain adaptation framework published last week in Transactions on Machine Learning Research (with a Featured Certification [Spotlight]!)
Reposted by Justin Kay
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/...
@cvprconference.bsky.social
Let's go: sites.google.com/view/fgvc12/...
@cvprconference.bsky.social
April 2, 2025 at 9:26 PM
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/...
@cvprconference.bsky.social
Let's go: sites.google.com/view/fgvc12/...
@cvprconference.bsky.social
The Computer Vision for Ecology program is organizing a 2-week remote workshop in May to teach AI methods to former US public sector scientists - Please consider sharing with your networks! We are also looking for volunteer instructors/mentors. Details here: cv4ecology.caltech.edu/ai-upskillin...
March 26, 2025 at 7:17 PM
The Computer Vision for Ecology program is organizing a 2-week remote workshop in May to teach AI methods to former US public sector scientists - Please consider sharing with your networks! We are also looking for volunteer instructors/mentors. Details here: cv4ecology.caltech.edu/ai-upskillin...
Reposted by Justin Kay
FGVC12 Workshop accepted to CVPR 2025, Nashville!
CALL FOR PAPERS: sites.google.com/view/fgvc12/...
We discuss domains where expert knowledge is typically required and investigate artificial systems that can efficiently distinguish a large number of very similar visual concepts.
#CVPR #CVPR2025 #AI
CALL FOR PAPERS: sites.google.com/view/fgvc12/...
We discuss domains where expert knowledge is typically required and investigate artificial systems that can efficiently distinguish a large number of very similar visual concepts.
#CVPR #CVPR2025 #AI
January 9, 2025 at 5:06 PM
FGVC12 Workshop accepted to CVPR 2025, Nashville!
CALL FOR PAPERS: sites.google.com/view/fgvc12/...
We discuss domains where expert knowledge is typically required and investigate artificial systems that can efficiently distinguish a large number of very similar visual concepts.
#CVPR #CVPR2025 #AI
CALL FOR PAPERS: sites.google.com/view/fgvc12/...
We discuss domains where expert knowledge is typically required and investigate artificial systems that can efficiently distinguish a large number of very similar visual concepts.
#CVPR #CVPR2025 #AI