PRO-VPT's Adaptive Distribution Optimization raises accuracy by 1.6 pp over standard VPT and hits state-of-the-art scores on VTAB-1k and FGVC; accepted at ICCV 2025. Read more: https://getnews.me/pro-vpt-adds-adaptive-visual-prompt-tuning-for-higher-accuracy/ #provpt #iccv2025
October 8, 2025 at 5:31 PM
PRO-VPT's Adaptive Distribution Optimization raises accuracy by 1.6 pp over standard VPT and hits state-of-the-art scores on VTAB-1k and FGVC; accepted at ICCV 2025. Read more: https://getnews.me/pro-vpt-adds-adaptive-visual-prompt-tuning-for-higher-accuracy/ #provpt #iccv2025
A new two‑stage saccadic vision model, mimicking human eye movements, was tested on FGVC datasets like CUB‑200‑2011 and Food‑101. The paper was submitted on September 19, 2025. https://getnews.me/saccadic-vision-improves-fine-grained-image-classification/ #saccadicvision #fgvc
September 22, 2025 at 10:48 AM
A new two‑stage saccadic vision model, mimicking human eye movements, was tested on FGVC datasets like CUB‑200‑2011 and Food‑101. The paper was submitted on September 19, 2025. https://getnews.me/saccadic-vision-improves-fine-grained-image-classification/ #saccadicvision #fgvc
Meet Ahmed Belgacem! 👋 Ahmed is an AI research engineer at Multitel with a focus on fine-grained classification. His debut article reveals a refined training recipe for FGVC that works on resource-constrained edge devices.
A Refined Training Recipe for Fine-Grained Visual Classification | Towards Data Science
How FGVC aims to recognize images belonging to multiple subordinate categories of a super-category
towardsdatascience.com
August 21, 2025 at 7:57 PM
Meet Ahmed Belgacem! 👋 Ahmed is an AI research engineer at Multitel with a focus on fine-grained classification. His debut article reveals a refined training recipe for FGVC that works on resource-constrained edge devices.
Congratulations to the winning teams from FathomNet's 2025 Kaggle Competition! Several winning teams discovered that looking at the bigger picture improved their results. 🧵
#Kaggle #CVPR2025 #FGVC #CV4Ecology #FathomNet
#Kaggle #CVPR2025 #FGVC #CV4Ecology #FathomNet
August 21, 2025 at 3:42 PM
Congratulations to the winning teams from FathomNet's 2025 Kaggle Competition! Several winning teams discovered that looking at the bigger picture improved their results. 🧵
#Kaggle #CVPR2025 #FGVC #CV4Ecology #FathomNet
#Kaggle #CVPR2025 #FGVC #CV4Ecology #FathomNet
We extend our gratitude to Kaggle, the FGVC Workshop organizers, and the hashtag#CV4Ecology Workshop Series for their continued support.
August 13, 2025 at 9:45 PM
We extend our gratitude to Kaggle, the FGVC Workshop organizers, and the hashtag#CV4Ecology Workshop Series for their continued support.
Рафинированный рецепт обучения для тонкой визуальной классификации
Как FGVC (Fine-Grained Visual Classification) стремится распознавать изображения, принадлежащие к нескольким подчиненным категориям суперкатегории
#ai #news
Как FGVC (Fine-Grained Visual Classification) стремится распознавать изображения, принадлежащие к нескольким подчиненным категориям суперкатегории
#ai #news
A Refined Training Recipe for Fine-Grained Visual Classification
towardsdatascience.com
August 13, 2025 at 9:38 PM
A Refined Training Recipe for Fine-Grained Visual Classification
How FGVC aims to recognize images belonging to multiple subordinate categories of a super-category
#ai #news
How FGVC aims to recognize images belonging to multiple subordinate categories of a super-category
#ai #news
A Refined Training Recipe for Fine-Grained Visual Classification
How FGVC aims to recognize images belonging to multiple subordinate categories of a super-category
towardsdatascience.com
August 13, 2025 at 7:37 PM
How do you get a general-purpose model like ResNet-50 to perform well on FGVC tasks? Ahmed Belgacem's debut TDS article breaks down a refined training recipe, demonstrating how techniques like TrivialAugment and Label Smoothing can compound to deliver a significant performance boost.
A Refined Training Recipe for Fine-Grained Visual Classification | Towards Data Science
How FGVC aims to recognize images belonging to multiple subordinate categories of a super-category
towardsdatascience.com
August 12, 2025 at 8:23 PM
How do you get a general-purpose model like ResNet-50 to perform well on FGVC tasks? Ahmed Belgacem's debut TDS article breaks down a refined training recipe, demonstrating how techniques like TrivialAugment and Label Smoothing can compound to deliver a significant performance boost.
Published last week at the CVPR FGVC Workshop; our paper on "Predicting butterfly species presence from satellite imagery using soft contrastive regularisation".
PDF (with links to data/code) available here:
openaccess.thecvf.com/content/CVPR...
PDF (with links to data/code) available here:
openaccess.thecvf.com/content/CVPR...
CVPR 2025 Open Access Repository
openaccess.thecvf.com
June 17, 2025 at 9:57 AM
Published last week at the CVPR FGVC Workshop; our paper on "Predicting butterfly species presence from satellite imagery using soft contrastive regularisation".
PDF (with links to data/code) available here:
openaccess.thecvf.com/content/CVPR...
PDF (with links to data/code) available here:
openaccess.thecvf.com/content/CVPR...
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
We will be in room 104E.
#FGVC #CVPR2025
@fgvcworkshop.bsky.social
June 11, 2025 at 12:56 PM
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
We will be in room 104E.
#FGVC #CVPR2025
@fgvcworkshop.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
sites.google.com/view/fgvc12
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
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
June 9, 2025 at 10:43 AM
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
sites.google.com/view/fgvc12
Cars, FGVC-Aircraft, and DTD) demonstrate that our approach consistently outperforms existing SEMs by a notable margin, with 4.2%-8.7% relative gains in 5-way 5-shot classification.These findings highlight the efficacy of coupling concept learning [7/8 of https://arxiv.org/abs/2506.04673v1]
June 6, 2025 at 6:01 AM
Cars, FGVC-Aircraft, and DTD) demonstrate that our approach consistently outperforms existing SEMs by a notable margin, with 4.2%-8.7% relative gains in 5-way 5-shot classification.These findings highlight the efficacy of coupling concept learning [7/8 of https://arxiv.org/abs/2506.04673v1]
arXiv:2505.23031v1 Announce Type: new
Abstract: In recent years, Fine-Grained Visual Classification (FGVC) has achieved impressive recognition accuracy, despite minimal inter-class variations. However, existing methods heavily rely on instance-level [1/6 of https://arxiv.org/abs/2505.23031v1]
Abstract: In recent years, Fine-Grained Visual Classification (FGVC) has achieved impressive recognition accuracy, despite minimal inter-class variations. However, existing methods heavily rely on instance-level [1/6 of https://arxiv.org/abs/2505.23031v1]
May 30, 2025 at 6:00 AM
arXiv:2505.23031v1 Announce Type: new
Abstract: In recent years, Fine-Grained Visual Classification (FGVC) has achieved impressive recognition accuracy, despite minimal inter-class variations. However, existing methods heavily rely on instance-level [1/6 of https://arxiv.org/abs/2505.23031v1]
Abstract: In recent years, Fine-Grained Visual Classification (FGVC) has achieved impressive recognition accuracy, despite minimal inter-class variations. However, existing methods heavily rely on instance-level [1/6 of https://arxiv.org/abs/2505.23031v1]
masks and features. We employ bidirectional consistency loss to regulate the classification outcomes across different hierarchies, ensuring label prediction consistency and reducing misclassification. Experiments on three widely used FGVC datasets [4/5 of https://arxiv.org/abs/2504.13608v1]
April 21, 2025 at 6:03 AM
masks and features. We employ bidirectional consistency loss to regulate the classification outcomes across different hierarchies, ensuring label prediction consistency and reducing misclassification. Experiments on three widely used FGVC datasets [4/5 of https://arxiv.org/abs/2504.13608v1]
arXiv:2504.13608v1 Announce Type: new
Abstract: Fine-Grained Visual Classification (FGVC) aims to categorize closely related subclasses, a task complicated by minimal inter-class differences and significant intra-class variance. Existing methods [1/5 of https://arxiv.org/abs/2504.13608v1]
Abstract: Fine-Grained Visual Classification (FGVC) aims to categorize closely related subclasses, a task complicated by minimal inter-class differences and significant intra-class variance. Existing methods [1/5 of https://arxiv.org/abs/2504.13608v1]
April 21, 2025 at 6:03 AM
arXiv:2504.13608v1 Announce Type: new
Abstract: Fine-Grained Visual Classification (FGVC) aims to categorize closely related subclasses, a task complicated by minimal inter-class differences and significant intra-class variance. Existing methods [1/5 of https://arxiv.org/abs/2504.13608v1]
Abstract: Fine-Grained Visual Classification (FGVC) aims to categorize closely related subclasses, a task complicated by minimal inter-class differences and significant intra-class variance. Existing methods [1/5 of https://arxiv.org/abs/2504.13608v1]
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]
👉 www.kaggle.com/competitions...
@cvprconference.bsky.social @kaggle.com
#FGVC #CVPR #CVPR2025 QIM Center (qim.dk)
[1/5]
April 15, 2025 at 7:21 AM
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]
👉 www.kaggle.com/competitions...
@cvprconference.bsky.social @kaggle.com
#FGVC #CVPR #CVPR2025 QIM Center (qim.dk)
[1/5]
enhancing sensitivity to fine details. GFT achieves SOTA accuracy on FGVC Aircraft, Food-101, and COCO datasets with 93M parameters, outperforming ViT-based advanced FGIC models in efficiency. By bridging global context and localized detail [6/7 of https://arxiv.org/abs/2504.09852v1]
April 15, 2025 at 6:20 AM
enhancing sensitivity to fine details. GFT achieves SOTA accuracy on FGVC Aircraft, Food-101, and COCO datasets with 93M parameters, outperforming ViT-based advanced FGIC models in efficiency. By bridging global context and localized detail [6/7 of https://arxiv.org/abs/2504.09852v1]
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]
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]
www.kaggle.com/competitions...
@fathomnet.bsky.social @fathomverse.bsky.social @mbarinews.bsky.social
@cvprconference.bsky.social @kaggle.com
#FGVC #CVPR #CVPR2025
[1/5]
April 8, 2025 at 11:17 PM
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]
www.kaggle.com/competitions...
@fathomnet.bsky.social @fathomverse.bsky.social @mbarinews.bsky.social
@cvprconference.bsky.social @kaggle.com
#FGVC #CVPR #CVPR2025
[1/5]
AnimalCLEF25: Multi-species individual animal identification
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 8, 2025 at 4:25 PM
AnimalCLEF25: Multi-species individual animal identification
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]
GeoLifeCLEF25: Location-based species presence prediction
👉 www.kaggle.com/competitions...
@cvprconference.bsky.social @kaggle.com
#FGVC #CVPR #CVPR2025 #LifeCLEF
[1/3]
👉 www.kaggle.com/competitions...
@cvprconference.bsky.social @kaggle.com
#FGVC #CVPR #CVPR2025 #LifeCLEF
[1/3]
April 7, 2025 at 10:36 PM
GeoLifeCLEF25: Location-based species presence prediction
👉 www.kaggle.com/competitions...
@cvprconference.bsky.social @kaggle.com
#FGVC #CVPR #CVPR2025 #LifeCLEF
[1/3]
👉 www.kaggle.com/competitions...
@cvprconference.bsky.social @kaggle.com
#FGVC #CVPR #CVPR2025 #LifeCLEF
[1/3]
PlantCLEF25: Multi-species plant identification in vegetation quadrat images
👉 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 7, 2025 at 10:13 AM
PlantCLEF25: Multi-species plant identification in vegetation quadrat images
👉 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]
FungiCLEF25: Few-shot classification with rare fungi species
👉 www.kaggle.com/competitions...
@cvprconference.bsky.social @kaggle.com
#FGVC #CVPR #CVPR2025 #LifeCLEF [1/2]
👉 www.kaggle.com/competitions...
@cvprconference.bsky.social @kaggle.com
#FGVC #CVPR #CVPR2025 #LifeCLEF [1/2]
April 4, 2025 at 12:47 PM
FungiCLEF25: Few-shot classification with rare fungi species
👉 www.kaggle.com/competitions...
@cvprconference.bsky.social @kaggle.com
#FGVC #CVPR #CVPR2025 #LifeCLEF [1/2]
👉 www.kaggle.com/competitions...
@cvprconference.bsky.social @kaggle.com
#FGVC #CVPR #CVPR2025 #LifeCLEF [1/2]
The deadline for non-archival short paper submissions to the FGVC workshop at #CVPR2025 as been extended by a few days.
sites.google.com/view/fgvc12
@cvprconference.bsky.social
sites.google.com/view/fgvc12
@cvprconference.bsky.social
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/...
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
March 31, 2025 at 12:57 PM
The deadline for non-archival short paper submissions to the FGVC workshop at #CVPR2025 as been extended by a few days.
sites.google.com/view/fgvc12
@cvprconference.bsky.social
sites.google.com/view/fgvc12
@cvprconference.bsky.social