Accepted 8-page proceedings and non-archival 4-page extended abstracts for FGVC12 can be accessed below.

We are very grateful for all the contributions to the workshop and for the continuous support of all reviewers listed at the bottom! 

PROCEEDINGS TRACK (8-PAGES)
The CVPRW 2025 proceedings can be accessed here: https://openaccess.thecvf.com/CVPR2025_workshops/FGVC 

FungiTastic: A Multi-Modal Dataset and Benchmark for Image Categorization
Lukas Picek (INRIA / University of West Bohemia); Vojtech Cermak (Czech Technical University in Prague); Jiri Matas (Czech Technical University in Prague); Klara Janouskova (Czech Technical University in Prague)

Fine-grained Few-Shot Classification with Part Matching
Samuel Black (Temple University); Richard Souvenir (Temple University)

CYFLOD: Cyclic Filtering and Loss Damping for Alleviating Noisy Labels in Fine-grained Visual Classification
Nauman Ullah Gilal (Hamad Bin Khalifa University); Khaled Al Thelaya (Hamad Bin Khalifa University); Fahad Majeed (Hamad Bin Khalifa University); Zhihe Lu (Hamad Bin Khalifa University); Sabri Boughorbel (Hamad Bin Khalifa University); Jens Schneider (Hamad Bin Khalifa University); Marco Agus (Hamad Bin Khalifa University)

Real-Time Ultra-Fine-Grained Surgical Instrument Classification
Md. Atabuzzaman (Virginia Tech); Gino DiMatteo (Virginia Tech); Hani Alomari (Virginia Tech); Chiawei Tang (Virginia Tech); Connor Hale (Carilion Clinic Innovations); Adam E. Goode (Carilion Clinic – Virginia Tech Carilion School of Medicine); David Ryan King (Carilion Clinic); Chris Thomas (Virginia Tech)

A Visual RAG Pipeline for Few-Shot Fine-Grained Product Classification
Bianca Lamm (Offenburg University); Janis Keuper (Offenburg University)

WildlifeReID-10k: Wildlife Re-identification Dataset with 10k Individual Animals
Lukas Adam (University of West Bohemia); Vojtech Cermak (Czech Technical University); Kostas Papafitsoros (Queen Mary University of London); Lukas Picek (INRIA / University of West Bohemia)

Multi-entity Video Transformers for Fine-Grained Video Representation Learning
Matthew Walmer (University of Maryland); Rose Kanjirathinkal (Meta); Kai Sheng Tai (Meta); Keyur Muzumdar (Meta); Taipeng Tian (Meta); Abhinav Shrivastava (University of Maryland)

Multi-aspect Knowledge Distillation with Large Language Model
Taegyeong Lee (UNIST); Jinsik Bang (UNIST); Soyeong Kwon (UNIST); Taehwan Kim (UNIST)

Self-Supervised Pretraining for Fine-Grained Plankton Recognition
Joona Kareinen (LUT University); Tuomas Eerola (LUT University); Kaisa Kraft (SYKE); Lasse Lensu (LUT University); Sanna Suikkanen (SYKE); Heikki Kälviäinen (LUT University)

Combining Vision-Language Models and Weak Supervision for Nuanced Vision Classification Tasks
Seyed Mohamad Ali Tousi (University of Missouri – Columbia); Jacket Demby’s (University of Missouri – Columbia); Ramy Farag (University of Missouri – Columbia); Gbenga Omotara (University of Missouri – Columbia); Guilherme N. DeSouza (University of Missouri – Columbia)

Pseudo-labelling Meets Label Smoothing for Noisy Partial Label Learning
Darshana Saravanan (IIIT Hyderabad); Naresh Manwani (IIIT Hyderabad); Vineet Gandhi (IIIT Hyderabad)

Predicting Butterfly Species Presence from Satellite Imagery Using Soft Contrastive Regularisation
Thijs van der Plas (Alan Turing Institute); Stephen Law (UCL); Michael Pocock (UK Centre for Ecology & Hydrology)

A Fine-grained Artist Identification Method for Authentication and Attribution of Drawings Using Hatching Lines
Shahrzad Ziaee (Rutgers University); Ahmed Elgammal (Rutgers University); Marian Mazzone (College of Charleston)

NON-ARCHIVAL TRACK (4-PAGES)

Does Feasibility Matter? Understanding the Impact of Feasibility on Synthetic Training Data

Yiwen Liu (Technical University of Munich); Jessica Bader (Helmholtz Munich / Technical University of Munich); Jae Myung Kim (Eberhard Karls Universität Tübingen)

[pdf]

Visual Variational Autoencoder Prompt Tuning

Xi Xiao (University of Alabama at Birmingham); Yunbei Zhang (Tulane University); Yanshu Li (Brown University); Xingjian Li (Carnegie Mellon University); Tianyang Wang (University of Alabama at Birmingham); Jihun Hamm (Tulane University); Xiao Wang (Oak Ridge National Laboratory); Min Xu (Carnegie Mellon University)

[pdf]

Rethinking Semi-Supervised Domain Adaptation for Semantic Segmentation in the Era of Foundation Models

Joshua Kurien (University of Waterloo); Bavesh Balaji (University of Waterloo); Kwei-Herng Lai (Apple); Pablo Guerrero Vela (Apple); C Thomas (Apple); Alexander Wong (Apple); Sirisha Rambhatla (University of Waterloo)

[pdf]

Quantifying Duplication in CLIP Training and Fine-Grained Classification Datasets

Le Sun (George Washington University); Alper Cetinkaya (George Washington University); Grady McPeak (George Washington University); Kevin Robbins (George Washington University); Shrenik Borad (George Washington University); Abby Stylianou (Saint Louis University); Robert Pless (George Washington University)

[pdf]

Investigating Different Geo Priors for Image Classification

Angela Zhu (University of Massachusetts Amherst); Christian Lange (The University of Edinburgh); Max Hamilton (University of Massachusetts Amherst)

[pdf]

NECTAR TRACK 

Few-Shot Recognition via Stage-Wise Retrieval-Augmented Finetuning

Tian Liu (Texas A&M University)

[pdf]

Fish-Vista: A Multi-Purpose Dataset for Understanding & Identification of Traits from Images

Kazi Sajeed Mehrab (Virginia Tech); M. Maruf (Virginia Tech); Arka Daw (Oak Ridge National Laboratory); Abhilash Neog (Virginia Tech); Harish Babu Manogaran (Virginia Tech); Mridul Khurana (Virginia Tech); Zhenyang Feng (The Ohio State University); Bahadir Altintas (Tulane University); Yasin Bakis (Tulane University); Elizabeth G Campolongo (The Ohio State University); Matthew J Thompson (The Ohio State University); Xiaojun Wang (Tulane University); Hilmar Lapp (Duke University); Tanya Berger-Wolf (The Ohio State University); Paula Mabee (Battelle); Henry Bart (Tulane University); Wei-Lun Chao (The Ohio State University); Wasila Dahdul (University of California, Irvine); Anuj Karpatne (Virginia Tech)

[pdf]

The GOOSE Dataset for Perception in Unstructured Environments

Peter Mortimer (Universität der Bundeswehr München); Raphael Hagmanns (Fraunhofer IOSB); Miguel Granero (Fraunhofer IOSB); Thorsten Luettel (Universität der Bundeswehr München); Janko Petereit (Fraunhofer IOSB)

[pdf]

Reviewers

We are very grateful for the continuous support of all reviewers! 

Alex Pujol Vidal

Alexis Joly

Ananthu Aniraj

Christian Lange

Elijah Cole

Hongbo Sun

Jiri Matas

Joakim Haurum

Justin Kay

Klára Janoušková

Levi Cai

Lukas Picek

Magnus Gjerde

Malte Pedersen

Mehmet Aygün

Mustafa Taha Kocyigit

Neelu Madan

Nico Lang

Oisin Mac Aodha

Peter Ebert Christensen

Rikke Gade

Rupa Kurinchi-Vendhan

Sander Jyhne

Shir Bar

Stefan Hein Bengtson

Subhransu Maji

Tarun Sharma

Timm Haucke

Tomáš Karella

Vaclav Divis

Vasiliki Ismiroglou