Poster board assignment: here

Accepted 8-page proceedings and non-archival 4-page extended abstracts for FGVC13 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 2026 proceedings can be accessed here: https://openaccess.thecvf.com/CVPR2026_workshops/FGVC13

Agentic Prompt Optimization with Visual Contrastive Reasoning for Fine-Grained Classification
Lucas Goncalves (Amazon)*; Robert Barton (Amazon); Vidit Bansal (Amazon); Karim Bouyarmane (Amazon)

Positive-First Most Ambiguous: A Simple Active Learning Criterion for Interactive Retrieval of Rare Categories
Kawtar Zaher (Institut National de Recherche en Informatique et Robotique (Inria) - Institut National de l'Audiovisuel (Ina))*; Olivier Buisson (Institut National de l'Audiovisuel); Alexis Joly (INRIA, LIRMM, Universite de Montpellier)

Masked Autoencoders with Limited Data: Does It Work? A Fine-Grained Bioacoustics Case Study
Wuao Liu (University of Massachusetts Amherst)*; Mustafa Chasmai (University of Massachusetts Amherst); Subhransu Maji (University of Massachusetts Amherst); Grant Van Horn (University of Massachusetts Amherst)

Efficient Fine-grained Image Retrieval with Vision Foundation Models for Industrial Objects
Yushi Liu (Bosch Reserach)*; Christian Graf (Bosch Reserach); Markus Spies (Bosch Research); Margret Keuper (University of Mannheim)

NON-ARCHIVAL TRACK (4-PAGES)

Beyond Flat Labels: Level-Restricted Contrastive Learning for Hierarchical Fine-Grained Vision Classification

Zhiyuan Tao (The Ohio State University); Srikumar Sastry (WUSTL); Matthew Thompson (The Ohio State University); Elizabeth Campolongo (The Ohio State University); Net Zhang (The Ohio State University); Ziheng Zhang (The Ohio State University); Hilmar Lapp (Duke University); Yu Su (The Ohio State University); Tanya Berger-Wolf (The Ohio State University); Nathan Jacobs (WUSTL); Wei-Lun Chao (Boston University); Jianyang Gu (The Ohio State University)*

[pdf]

Training-Free Fine-Grained Semantic Segmentations in Low Data Regimes: A FungiTastic Baseline

Sebastian Cavada (Covision Lab); Francesco Pelosin (Covision Lab)*; Lapo Faggi (Covision Lab)

[pdf]

The Loupe: A Plug-and-Play Attention Module for Amplifying Discriminative Features in Vision Transformers

Naren Sengoden (JAIN University)*

[pdf]

BareBones - Benchmarking Zero-Shot Geometric Comprehension in VLMs

Aaditya Baranwal (University of Central Florida)*; Vishal Yadav (Independent Researcher); Abhishek Rajora (University of Calgary)

[pdf]

Zero-Shot Concept Bottlenecks: A Reality Check

Rajeev Datta (Cornell University)*; Cheng Perng Phoo (Waymo); Carl Vondrick (Columbia University); Kavita Bala (Cornell University); Bharath Hariharan (Cornell University); Utkarsh Mall (Mohamed bin Zayed University of Artificial Intelligence)

[pdf] [suppl]

Pretraining Objective Matters in Extreme Low-Data FGVC: A Backbone-Controlled Study

Alexander Hackett (Santa Clara University)*; Srikanth Thudumu (Institute of Applied Artificial Intelligence and Robotics (IAAIR)); Ginny Fisher (Institute of Applied Artificial Intelligence and Robotics (IAAIR)); Jason Fisher (Institute of Applied Artificial Intelligence and Robotics (IAAIR))

[pdf]

DistortBench: Benchmarking Vision Language Models on Image Distortion Identification

Divyanshu Goyal (Adobe)*; Akhil Eppa (Adobe); Vanya Bannihatti Kumar (Carnegie Mellon University)

[pdf]

Perceptual Loss-Based Approaches to Personal Color Season Classification

Witsanupong  Kolakul (Uphasia Artificial Intelligence); Pasin Buakhaw (Chulalongkorn University)*; Suchitra  Sueeprasan (Chulalongkorn University)

[pdf]

Structural Connectivity with Spring Energy for Fine-Grained Captioning in Large Vision-Language Models
Hidetomo Sakaino (FPT); Nguyen Nam (F)*

[pdf]

Node-Level Gating for Long-Tailed Recognition under Neural Collapse Geometry

Hyeontaek Hwang (Korea Advanced Institue of Science and Technology)*; Cheonghwan Hur (RTST Inc.); Daeyoung Kim (Korea Advanced Institue of Science and Technology)

[pdf]

Enhancing Identification Pipelines via Candidate-Aware Reranking

Grigory Demidov (Higher School of Economics)*; Roman Pakhomov (Innopolis University); Svyatoslav Lanskikh (Central University); Danis Dinmukhametov (Higher School of Economics); Andrey Khlopotnukh (Higher School of Economics); Kristian Bogdan (Central University); Elisey Kirpichenko (self-employed)

[pdf]

How to Choose Your Teacher for Fine Grained Image Recognition

Oswin Gosal (NTHU); Edwin  Rios  (NYCU)*; Augusto  Surya (NTHU); Fernando  Mikael  (NTHU); Bo-Cheng Lai  (NYCU); Min-Chun Hu  (NTHU)

[pdf]

A Multi-Phase Pipeline for Efficient, Vehicle-Based Pest Detection and Classification in Precision Agriculture

Bennett Huang (Langley High School)*; Jason Pan (Langley High School)

[pdf]

A Large-Scale Study on the Accuracy vs Cost Trade-offs of Training and Evaluation Settings in Fine-Grained Image Recognition

Edwin Rios (National Yang Ming Chiao Tung University)*; Augusto Christian Surya (National Tsing Hua University); Oswin Gosal (National Tsing Hua University); Fernando Mikael (National Tsing Hua University); Mary Nicole (National Tsing Hua University); Kisoon Jang (National Tsing Hua University); Bo-Cheng Lai (National Yang Ming Chiao Tung University); Min-Chun Hu (National Tsing Hua University)

[pdf]

What Does an OCR Model Look At? Probing Implicit Component Discrimination in Deepseek-OCR

Johnathan Han (Algoverse AI Research); Samik Barman (Algoverse AI Research); Lening Cui (Vanderbilt University)*; Ruizhe Li (Algoverse AI Research); Kevin Zhu (Algoverse AI Research)

[pdf]

NECTAR TRACK 

Challenges for computer vision as a tool for screening urban trees through street-view images
Jose Delpiano (University of the Andes)*
[pdf]

From Visual to Multimodal: Systematic Ablation of Encoders and Fusion Strategies in Animal Identification
Vasiliy Kudryavtsev (MTUCI); Kirill Borodin (MTUCI)*; German Berezin (MTUCI); Kirill Bubenchikov (Avito); Grach Mkrtchian (MTUCI); Alexander Ryzhkov (AVITO)
[pdf]

LiteEmbed: Adapting CLIP to Rare Classes
Aishwarya Agarwal (Adobe Research)*; Srikrishna Karanam (Adobe Research); Vineet Gandhi (IIIT Hyderabad)
[pdf]

Not All Birds Look The Same: Identity-Preserving Generation For Birds
Aaron Sun (University of Massachusetts, Amherst)*; Oindrila Saha (University of Massachusetts, Amherst); Subhransu Maji (University of Massachusetts, Amherst)
[pdf]

Indexing Multimodal Language Models for Large-scale Image Retrieval
Bahey Tharwat (MBZUAI)*; Giorgos Kordopatis-Zilos (VRG, FEE, Czech Technical University in Prague); Pavel Suma (VRG, FEE, Czech Technical University in Prague); Ian Reid (MBZUAI); Giorgos Tolias (VRG, FEE, Czech Technical University in Prague)
[pdf]

Local-Global Prompt Learning via Sparse Optimal Transport
Deniz Kizaroglu (Middle East Technical University); Ülkü Tuncer Küçüktaş (Gazi University); Emre Çakmakyurdu (Middle East Technical University); Alptekin Temizel (Middle East Technical University)*
[pdf]

FungiTastic: A Multi-Modal Dataset and Benchmark for Image Categorization
Lukas Picek (MIT / 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)
[pdf]

Reviewers
Thank you!!