Fine-Grained Visual Classification of Aircraft

2013/06/21 by Subhransu Maji, Maji, Subhransu, Esa Rahtu +7 · 191 citations
Computer Science · Earth and Planetary Sciences · Engineering · #3D Surveying and Cultural Heritage #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image and Object Detection Techniques #Infrared Target Detection Methodologies

paper · pdf · doi:10.48550/arxiv.1306.5151

openalex publication_date 2013/06/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This paper introduces FGVC-Aircraft, a new dataset containing 10,000 images of aircraft spanning 100 aircraft models, organised in a three-level hierarchy. At the finer level, differences between models are often subtle but always visually measurable, making visual recognition challenging but possible. A benchmark is obtained by defining corresponding classification tasks and evaluation protocols, and baseline results are presented. The construction of this dataset was made possible by the work of aircraft enthusiasts, a strategy that can extend to the study of number of other object classes. Compared to the domains usually considered in fine-grained visual classification (FGVC), for example animals, aircraft are rigid and hence less deformable. They, however, present other interesting modes of variation, including purpose, size, designation, structure, historical style, and branding.

Cited by

• Same or Not? Enhancing Visual Perception in Vision-Language Models
• Decomposing Task Vectors for Refined Model Editing
• The Quest for Winning Tickets in Low-Rank Adapters
• FunnelAL: Retrieve-then-Rank Active Learning for Single-Class Discovery
• Hierarchy-Aware Fine-Tuning of Vision-Language Models
• Auxiliary Descriptive Knowledge for Few-Shot Adaptation of Vision-Language Model
• Retrieval-augmented Prompt Learning for Pre-trained Foundation Models
• SigLino: Efficient Multi-Teacher Distillation for Agglomerative Vision Foundation Models
• AmPLe: Supporting Vision-Language Models via Adaptive-Debiased Ensemble Multi-Prompt Learning
• Towards Ancient Plant Seed Classification: A Benchmark Dataset and Baseline Model
• TTP: Test-Time Padding for Adversarial Detection and Robust Adaptation on Vision-Language Models
• SuperCLIP: CLIP with Simple Classification Supervision
• Calibrating Uncertainty for Zero-Shot Adversarial CLIP
• MetaTPT: Meta Test-time Prompt Tuning for Vision-Language Models
• Advancing Cache-Based Few-Shot Classification via Patch-Driven Relational Gated Graph Attention
• Towards Fine-Grained Recognition with Large Visual Language Models: Benchmark and Optimization Strategies
• Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective
• Visual Species Recognition with Large Multimodal Models as Post-Hoc Correctors
• Training-Free Dual Hyperbolic Adapters for Better Cross-Modal Reasoning
• Decoupling Template Bias in CLIP: Harnessing Empty Prompts for Enhanced Few-Shot Learning
• Dropout Prompt Learning: Towards Robust and Adaptive Vision-Language Models
• ReLKD: Inter-Class Relation Learning with Knowledge Distillation for Generalized Category Discovery
• Neural Coherence : Find higher performance to out-of-distribution tasks from few samples
• Fourier-Attentive Representation Learning: A Fourier-Guided Framework for Few-Shot Generalization in Vision-Language Models
• Basis-Oriented Low-rank Transfer for Few-Shot and Test-Time Adaptation
• Partially Shared Concept Bottleneck Models
• Learning What Helps: Task-Aligned Context Selection for Vision Tasks
• PowerCLIP: Powerset Alignment for Contrastive Pre-Training
• ClearGCD: Mitigating Shortcut Learning For Robust Generalized Category Discovery
• From Points to Clouds: Learning Robust Semantic Distributions for Multi-modal Prompts
• VaMP: Variational Multi-Modal Prompt Learning for Vision-Language Models
• Semi-Supervised Contrastive Learning with Orthonormal Prototypes
• AnchorOPT: Towards Optimizing Dynamic Anchors for Adaptive Prompt Learning
• MetaRank: Task-Aware Metric Selection for Model Transferability Estimation
• CHIPS: Efficient CLIP Adaptation via Curvature-aware Hybrid Influence-based Data Selection
• DiVE-k: Differential Visual Reasoning for Fine-grained Image Recognition
• ATAC: Augmentation-Based Test-Time Adversarial Correction for CLIP
• ReBaPL: Repulsive Bayesian Prompt Learning
• Hierarchical Semantic Tree Anchoring for CLIP-Based Class-Incremental Learning
• HiGFA: Hierarchical Guidance for Fine-grained Data Augmentation with Diffusion Models
• BOFA: Bridge-Layer Orthogonal Low-Rank Fusion for CLIP-Based Class-Incremental Learning
• Heterogeneous Complementary Distillation
• Test-Time Spectrum-Aware Latent Steering for Zero-Shot Generalization in Vision-Language Models
• Doubly Debiased Test-Time Prompt Tuning for Vision-Language Models
• SWAP: Towards Copyright Auditing of Soft Prompts via Sequential Watermarking
• Decoupling Augmentation Bias in Prompt Learning for Vision-Language Models
• Decoupled Multi-Predictor Optimization for Inference-Efficient Model Tuning
• Generative Hints
• Generalized Category Discovery under Domain Shift: A Frequency Domain Perspective
• Learning an Efficient Optimizer via Hybrid-Policy Sub-Trajectory Balance
• FedMGP: Personalized Federated Learning with Multi-Group Text-Visual Prompts
• Soft Task-Aware Routing of Experts for Equivariant Representation Learning
• A Retrospect to Multi-prompt Learning across Vision and Language
• A-TPT: Angular Diversity Calibration Properties for Test-Time Prompt Tuning of Vision-Language Models
• When Prompts Ignore Structure: Graph-Based Attribute Reasoning for Calibrated VLMs
• Attentive multilayer fusion for vision transformers
• On the Provable Importance of Gradients for Language-Assisted Image Clustering
• Enhancing CLIP Robustness via Cross-Modality Alignment
• Beyond Objects: Contextual Synthetic Data Generation for Fine-Grained Classification
• MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding
• Implicit Modeling for Transferability Estimation of Vision Foundation Models
• Self-Calibrated Consistency can Fight Back for Adversarial Robustness in Vision-Language Models
• Memory-Free Continual Learning with Null Space Adaptation for Zero-Shot Vision-Language Models
• Bi-CoG: Bi-Consistency-Guided Self-Training for Vision-Language Models
• Class-Aware Prototype Learning with Negative Contrast for Test-Time Adaptation of Vision-Language Models
• Theoretical Refinement of CLIP by Utilizing Linear Structure of Optimal Similarity
• FPT-Noise: Dynamic Scene-Aware Counterattack for Test-Time Adversarial Defense in Vision-Language Models
• SEAL: Semantic-Aware Hierarchical Learning for Generalized Category Discovery
• Learning Task-Agnostic Representations through Multi-Teacher Distillation
• Elastic ViTs from Pretrained Models without Retraining
• You May Speak Freely: Improving the Fine-Grained Visual Recognition Capabilities of Multimodal Large Language Models with Answer Extraction
• Free-Grained Hierarchical Recognition
• Exploring Cross-Modal Flows for Few-Shot Learning
• Salient Concept-Aware Generative Data Augmentation
• Seeing and Knowing in the Wild: Open-domain Visual Entity Recognition with Large-scale Knowledge Graphs via Contrastive Learning
• microCLIP: Unsupervised CLIP Adaptation via Coarse-Fine Token Fusion for Fine-Grained Image Classification
• Cluster-Aware Prompt Ensemble Learning for Few-Shot Vision-Language Model Adaptation
• PHyCLIP: ℓ₁-Product of Hyperbolic Factors Unifies Hierarchy and Compositionality in Vision-Language Representation Learning
• D-TPT: Dimensional Entropy Maximization for Calibrating Test-Time Prompt Tuning in Vision-Language Models
• Revisiting Pose-Normalization for Fine-Grained Few-Shot Recognition
• How NOT to benchmark your SITE metric: Beyond Static Leaderboards and Towards Realistic Evaluation
• Beyond the Seen: Bounded Distribution Estimation for Open-Vocabulary Learning
• Zero-Shot Fine-Grained Image Classification Using Large Vision-Language Models
• NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search
• Improving Adversarial Robustness of Zero-Shot CLIP with Confidence-Aware Weighting
• Bayesian Test-time Adaptation for Object Recognition and Detection with Vision-language Models
• On-the-Fly Data Augmentation via Gradient-Guided and Sample-Aware Influence Estimation
• Zero-Shot Decentralized Federated Learning
• SeMoBridge: Semantic Modality Bridge for Efficient Few-Shot Adaptation of CLIP
• GenView++: Unifying Adaptive Generative Augmentation and Quality-Driven Supervision for Contrastive Representation Learning
• Robust Fine-Tuning from Non-Robust Pretrained Models: Mitigating Suboptimal Transfer With Adversarial Scheduling
• Sparse, Collaborative, or Nonnegative Representation: Which Helps Pattern Classification?
• When Does Self-supervision Improve Few-shot Learning?
• Hierarchical Representation Matching for CLIP-based Class-Incremental Learning
• PartCo: Part-Level Correspondence Priors Enhance Category Discovery
• Training-Free Synthetic Data Generation with Dual IP-Adapter Guidance
• Category Discovery: An Open-World Perspective
• Closing the Oracle Gap: Increment Vector Transformation for Class Incremental Learning
• EnGraf-Net: Multiple Granularity Branch Network with Fine-Coarse Graft Grained for Classification Task
• SiNGER: A Clearer Voice Distills Vision Transformers Further
• Unlocking Noise-Resistant Vision: Key Architectural Secrets for Robust Models
• ICONIC-444: A 3.1-Million-Image Dataset for OOD Detection Research
• Unifying Adversarially Robust Model Experts in Vision-Language Models
• Alternating Training-based Label Smoothing Enhances Prompt Generalization
• Attribute Mix: Semantic Data Augmentation for Fine Grained Recognition
• No Labels Needed: Zero-Shot Image Classification with Collaborative Self-Learning
• Global Prompt Refinement with Non-Interfering Attention Masking for One-Shot Federated Learning
• Learning Attribute-Aware Hash Codes for Fine-Grained Image Retrieval via Query Optimization
• Benchmarking and Mitigating MCQA Selection Bias of Large Vision-Language Models
• Emulating Human-like Adaptive Vision for Efficient and Flexible Machine Visual Perception
• Predicting Training Time Without Training
• Trade-offs in Cross-Domain Generalization of Foundation Model Fine-Tuned for Biometric Applications
• Constrained Prompt Enhancement for Improving Zero-Shot Generalization of Vision-Language Models
• Self Identity Mapping
• Vision-Language Models for Vision Tasks: A Survey
• Intriguing Properties of Vision Transformers
• Where to Focus: Deep Attention-based Spatially Recurrent Bilinear Networks for Fine-Grained Visual Recognition
• Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels
• Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization
• Bootstrap your own latent: A new approach to self-supervised Learning
• Fine-Grained Visual Classification via Simultaneously Learning of Multi-regional Multi-grained Features
• Fine-Grained Visual Classification with Efficient End-to-end Localization
• Customizing Student Networks From Heterogeneous Teachers via Adaptive Knowledge Amalgamation
• Logit Mixture Outlier Exposure for Fine-grained Out-of-Distribution Detection
• Rethinking Channel Dimensions for Efficient Model Design
• NAT: Learning to Attack Neurons for Enhanced Adversarial Transferability
• Representation Transfer by Optimal Transport
• Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network
• Intra-Ensemble in Neural Networks
• Hyperbolic Large Language Models
• Rethinking Supervised Pre-training for Better Downstream Transferring
• Towards Open World Detection: A Survey
• Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation
• Attn-Adapter: Attention Is All You Need for Online Few-shot Learner of Vision-Language Model
• Causality-guided Prompt Learning for Vision-language Models via Visual Granulation
• Singular Value Few-shot Adaptation of Vision-Language Models
• LogME: Practical Assessment of Pre-trained Models for Transfer Learning
• FedAPT: Federated Adversarial Prompt Tuning for Vision-Language Models
• DIET-CP: Lightweight and Data Efficient Self Supervised Continued Pretraining
• Rethinking FUN: Frequency-Domain Utilization Networks
• Spotlighter: Revisiting Prompt Tuning from a Representative Mining View
• NoiseCutMix: A Novel Data Augmentation Approach by Mixing Estimated Noise in Diffusion Models
• Language-Aware Information Maximization for Transductive Few-Shot CLIP
• Category-level Text-to-Image Retrieval Improved: Bridging the Domain Gap with Diffusion Models and Vision Encoders
• Representation Learning with Adaptive Superpixel Coding
• Occlusion Robustness of CLIP for Military Vehicle Classification
• Measuring Dataset Granularity
• Local Patch AutoAugment with Multi-Agent Collaboration
• UNIFORM: Unifying Knowledge from Large-scale and Diverse Pre-trained Models
• Backpropagation-Free Test-Time Adaptation via Probabilistic Gaussian Alignment
• Efficient Multi-Source Knowledge Transfer by Model Merging
• Flatness-aware Curriculum Learning via Adversarial Difficulty
• Transfer learning optimization based on evolutionary selective fine tuning
• The Loupe: A Plug-and-Play Attention Module for Amplifying Discriminative Features in Vision Transformers
• Enhancing Targeted Adversarial Attacks on Large Vision-Language Models via Intermediate Projector
• Channel DropBlock: An Improved Regularization Method for Fine-Grained Visual Classification
• Ranking and Tuning Pre-trained Models: A New Paradigm for Exploiting Model Hubs
• Preserve and Sculpt: Manifold-Aligned Fine-tuning of Vision-Language Models for Few-Shot Learning
• Cross-Domain Few-Shot Learning via Multi-View Collaborative Optimization with Vision-Language Models
• Federated Cross-Modal Style-Aware Prompt Generation
• AdaRing: Towards Ultra-Light Vision-Language Adaptation via Cross-Layer Tensor Ring Decomposition
• Noise Matters: Optimizing Matching Noise for Diffusion Classifiers
• Dissecting Generalized Category Discovery: Multiplex Consensus under Self-Deconstruction
• SemPT: Semantic Prompt Tuning for Vision-Language Models
• Compact Approximation for Polynomial of Covariance Feature
• The TCGA Meta-Dataset Clinical Benchmark
• Learn to Explore: Meta NAS via Bayesian Optimization Guided Graph Generation
• Continual Learning in Neural Networks
• AME: Aligned Manifold Entropy for Robust Vision-Language Distillation
• Transferable Model-agnostic Vision-Language Model Adaptation for Efficient Weak-to-Strong Generalization
• A Guide to Robust Generalization: The Impact of Architecture, Pre-training, and Optimization Strategy
• Adaptive Cache Enhancement for Test-Time Adaptation of Vision-Language Models
• Separation and Collaboration: Two-Level Routing Grouped Mixture-of-Experts for Multi-Domain Continual Learning
• BadPromptFL: A Novel Backdoor Threat to Prompt-based Federated Learning in Multimodal Models
• Adapting Vision-Language Models Without Labels: A Comprehensive Survey
• FixyNN: Efficient Hardware for Mobile Computer Vision via Transfer\n Learning
• ETTA: Efficient Test-Time Adaptation for Vision-Language Models through Dynamic Embedding Updates
• Robust Prompt Tuning for Vision-Language Models with Mild Semantic Noise
• UniFGVC: Universal Training-Free Few-Shot Fine-Grained Vision Classification via Attribute-Aware Multimodal Retrieval
• Causal Disentanglement and Cross-Modal Alignment for Enhanced Few-Shot Learning
• FedPromo: Federated Lightweight Proxy Models at the Edge Bring New Domains to Foundation Models
• Raw Data Matters: Enhancing Prompt Tuning by Internal Augmentation on Vision-Language Models
• EvoVLMA: Evolutionary Vision-Language Model Adaptation
• Multi-Cache Enhanced Prototype Learning for Test-Time Generalization of Vision-Language Models
• Decouple before Align: Visual Disentanglement Enhances Prompt Tuning
• FaceGCD: Generalized Face Discovery via Dynamic Prefix Generation
• Color as the Impetus: Transforming Few-Shot Learner
• MetaLab: Few-Shot Game Changer for Image Recognition
• Fine-Grained Categorization via CNN-Based Automatic Extraction and Integration of Object-Level and Part-Level Features
• MSGCoOp: Multiple Semantic-Guided Context Optimization for Few-Shot Learning
• Adversarial Reconstruction Feedback for Robust Fine-grained Generalization

Related

• cofga: A Dataset for Fine Grained Classification of Objects from Aerial Imagery
• ELoPE: Fine-Grained Visual Classification with Efficient Localization, Pooling and Embedding
• Intelligent Known and Novel Aircraft Recognition -- A Shift from Classification to Similarity Learning for Combat Identification
• COFGA: Classification Of Fine-Grained Features In Aerial Images
• Webly Supervised Fine-Grained Recognition: Benchmark Datasets and An Approach