Fine-Grained Visual Classification of Aircraft

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 in corpus (222)

• A Simple Framework for Contrastive Learning of Visual Representations
• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
• Bootstrap your own latent: A new approach to self-supervised Learning
• Learning to Prompt for Vision-Language Models
• A continual learning survey: Defying forgetting in classification tasks
• A Survey of Deep Learning-based Object Detection
• DINOv2: Learning Robust Visual Features without Supervision
• AutoAugment: Learning Augmentation Policies from Data
• The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification
• Object-Part Attention Model for Fine-grained Image Classification
• Deep Image: Scaling up Image Recognition
• Intriguing Properties of Vision Transformers
• Pruning by Explaining: A Novel Criterion for Deep Neural Network Pruning
• BSNet: Bi-Similarity Network for Few-shot Fine-grained Image Classification
• Neural Architecture Transfer
• Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications
• The Devil is in the Tails: Fine-grained Classification in the Wild
• Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling
• ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulation
• Heterogeneous Domain Generalization via Domain Mixup
• CLIP-Adapter: Better Vision-Language Models with Feature Adapters
• Deep CNNs Meet Global Covariance Pooling: Better Representation and Generalization
• CLIP-Art: Contrastive Pre-training for Fine-Grained Art Classification
• Multi-Objective Matrix Normalization for Fine-grained Visual Recognition
• See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classification
• Learning Semantically Enhanced Feature for Fine-Grained Image Classification
• An overview of mixing augmentation methods and augmentation strategies
• Part-guided Relational Transformers for Fine-grained Visual Recognition
• Dual Modality Prompt Tuning for Vision-Language Pre-Trained Model
• Deep Learning for Fine-Grained Image Analysis: A Survey
• Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples
• Fine-grained Visual-textual Representation Learning
• Bilinear CNNs for Fine-grained Visual Recognition
• Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metrics
• Self-supervised Learning is More Robust to Dataset Imbalance
• Rethinking the Hyperparameters for Fine-tuning
• BOIL: Towards Representation Change for Few-shot Learning
• CrossTransformers: spatially-aware few-shot transfer
• Contrastive Learning with Adversarial Examples
• A comparison of dense region detectors for image search and fine-grained classification
• A Constructive Prediction of the Generalization Error Across Scales
• Convolutional Fine-Grained Classification with Self-Supervised Target Relation Regularization
• K for the Price of 1: Parameter-efficient Multi-task and Transfer Learning
• Generalized BackPropagation, Étude De Cas: Orthogonality
• Radial Basis Function Networks for Convolutional Neural Networks to Learn Similarity Distance Metric and Improve Interpretability
• LogME: Practical Assessment of Pre-trained Models for Transfer Learning
• Open-Set Recognition: a Good Closed-Set Classifier is All You Need?
• Danish Fungi 2020 -- Not Just Another Image Recognition Dataset
• On the Eigenvalues of Global Covariance Pooling for Fine-grained Visual Recognition
• Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation
• FixyNN: Efficient Hardware for Mobile Computer Vision via Transfer Learning
• Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network
• Budget-Aware Adapters for Multi-Domain Learning
• Selective Convolutional Descriptor Aggregation for Fine-Grained Image Retrieval
• TinyTL: Reduce Activations, Not Trainable Parameters for Efficient On-Device Learning
• Deep Layer Aggregation
• Gradient Centralization: A New Optimization Technique for Deep Neural Networks
• Object Discovery From a Single Unlabeled Image by Mining Frequent Itemset With Multi-scale Features
• Improved Bilinear Pooling with CNNs
• Re-rank Coarse Classification with Local Region Enhanced Features for Fine-Grained Image Recognition
• Optimized Generic Feature Learning for Few-shot Classification across Domains
• Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning
• Improving COVID-19 CT Classification of CNNs by Learning Parameter-Efficient Representation
• Exploration of Class Center for Fine-Grained Visual Classification
• Scaling Laws for Deep Learning
• Scalable Transfer Learning with Expert Models
• Attributes Grouping and Mining Hashing for Fine-Grained Image Retrieval
• Salient Mask-Guided Vision Transformer for Fine-Grained Classification
• Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches
• GuidedMixup: An Efficient Mixup Strategy Guided by Saliency Maps
• Multi-branch and Multi-scale Attention Learning for Fine-Grained Visual Categorization
• Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distribution Tasks
• Beneficial Perturbation Network for designing general adaptive artificial intelligence systems
• How Good is Google Bard's Visual Understanding? An Empirical Study on Open Challenges
• Cross-X Learning for Fine-Grained Visual Categorization
• Hierarchical Bilinear Pooling for Fine-Grained Visual Recognition
• Revisiting Meta-Learning as Supervised Learning
• The iNaturalist Species Classification and Detection Dataset
• Amalgamating Knowledge towards Comprehensive Classification
• NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search
• When Does Self-supervision Improve Few-shot Learning?
• Guided Zoom: Questioning Network Evidence for Fine-grained Classification
• Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup
• Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization
• Rethinking Channel Dimensions for Efficient Model Design
• Continual Learning in Neural Networks
• Learning Adaptive Classifiers Synthesis for Generalized Few-Shot Learning
• Frustratingly Easy Transferability Estimation
• Bi-tuning of Pre-trained Representations
• Fair Comparison: Quantifying Variance in Resultsfor Fine-grained Visual Categorization
• Look-into-Object: Self-supervised Structure Modeling for Object Recognition
• Selecting Relevant Features from a Multi-domain Representation for Few-shot Classification
• Ranking and Tuning Pre-trained Models: A New Paradigm for Exploiting Model Hubs
• Rethinking Self-Supervised Learning: Small is Beautiful
• Rethinking FUN: Frequency-Domain Utilization Networks
• Customizing Student Networks From Heterogeneous Teachers via Adaptive Knowledge Amalgamation
• Fine-grained Recognition: Accounting for Subtle Differences between Similar Classes
• Large-Scale Classification of Structured Objects using a CRF with Deep Class Embedding
• Weakly Supervised Bilinear Attention Network for Fine-Grained Visual Classification
• Fine-to-coarse Knowledge Transfer For Low-Res Image Classification
• Fine-Grained Image Analysis with Deep Learning: A Survey
• Rethinking Supervised Pre-training for Better Downstream Transferring
• Cross-domain Few-shot Learning with Task-specific Adapters
• Playing to distraction: towards a robust training of CNN classifiers through visual explanation techniques
• Weak-shot Fine-grained Classification via Similarity Transfer
• SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data
• Boosting Binary Masks for Multi-Domain Learning through Affine Transformations
• Fine-Grained Visual Classification with Efficient End-to-end Localization
• XMixup: Efficient Transfer Learning with Auxiliary Samples by Cross-domain Mixup
• A Fine-Grained Vehicle Detection (FGVD) Dataset for Unconstrained Roads
• Unsupervised Part Mining for Fine-grained Image Classification
• Facing the Hard Problems in FGVC
• Measuring Dataset Granularity
• Improving Deep Representation Learning via Auxiliary Learnable Target Coding
• Deep Attentional Structured Representation Learning for Visual Recognition
• The TCGA Meta-Dataset Clinical Benchmark
• Self-Supervised Learning by Estimating Twin Class Distributions
• Distance-Based Regularisation of Deep Networks for Fine-Tuning
• Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets
• Two-sample Testing Using Deep Learning
• Predicting Training Time Without Training
• Catch-Up Mix: Catch-Up Class for Struggling Filters in CNN
• 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
• Visual Concept Recognition and Localization via Iterative Introspection
• A Unified Pruning Framework for Vision Transformers
• Backbone Can Not be Trained at Once: Rolling Back to Pre-trained Network for Person Re-Identification
• Non-negative Sparse and Collaborative Representation for Pattern Classification
• Learning a Robust Representation via a Deep Network on Symmetric Positive Definite Manifolds
• Sparse, Collaborative, or Nonnegative Representation: Which Helps Pattern Classification?
• Non-binary deep transfer learning for image classification
• Part-Stacked CNN for Fine-Grained Visual Categorization
• AdaFilter: Adaptive Filter Fine-tuning for Deep Transfer Learning
• Embedding Adaptation is Still Needed for Few-Shot Learning
• Boosting Supervision with Self-Supervision for Few-shot Learning
• Convolutional Neural Networks Do Work with Pre-Defined Filters
• CEKD:Cross Ensemble Knowledge Distillation for Augmented Fine-grained Data
• Low-rank Bilinear Pooling for Fine-Grained Classification
• Learning Granularity-Aware Convolutional Neural Network for Fine-Grained Visual Classification
• Sample-based Regularization: A Transfer Learning Strategy Toward Better Generalization
• Revisiting Pose-Normalization for Fine-Grained Few-Shot Recognition
• An empirical study of pretrained representations for few-shot classification
• Attribute Mix: Semantic Data Augmentation for Fine Grained Recognition
• AlphaNet: Improved Training of Supernets with Alpha-Divergence
• Intra-Ensemble in Neural Networks
• Improving Contrastive Learning by Visualizing Feature Transformation
• Provably Robust Detection of Out-of-distribution Data (almost) for free
• Effective Data Augmentation with Multi-Domain Learning GANs
• The iMaterialist Fashion Attribute Dataset
• Adversarial Training Helps Transfer Learning via Better Representations
• Beyond Self-Supervision: A Simple Yet Effective Network Distillation Alternative to Improve Backbones
• SMILE: Self-Distilled MIxup for Efficient Transfer LEarning
• Your "Flamingo" is My "Bird": Fine-Grained, or Not
• Learning Class Unique Features in Fine-Grained Visual Classification
• Downstream-Pretext Domain Knowledge Traceback for Active Learning
• Compositional Kronecker Context Optimization for Vision-Language Models
• Contextualizing Enhances Gradient Based Meta Learning
• Learning Visual Representations for Transfer Learning by Suppressing Texture
• Representation Transfer by Optimal Transport
• Neural Naturalist: Generating Fine-Grained Image Comparisons
• Learning Finer-class Networks for Universal Representations
• Fine-Grained Representation Learning and Recognition by Exploiting Hierarchical Semantic Embedding
• Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning
• Real Time Fine-Grained Categorization with Accuracy and Interpretability
• Write a Classifier: Predicting Visual Classifiers from Unstructured Text
• MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and Architectures
• Representation Consolidation for Training Expert Students
• Exploring Vision Transformers for Fine-grained Classification
• A Large-Scale Car Dataset for Fine-Grained Categorization and Verification
• Grad-CAM guided channel-spatial attention module for fine-grained visual classification
• Group Based Deep Shared Feature Learning for Fine-grained Image Classification
• Joint Learning of Neural Networks via Iterative Reweighted Least Squares
• Channel Interaction Networks for Fine-Grained Image Categorization
• ACE: Adaptive Confusion Energy for Natural World Data Distribution
• Convolutional Low-Resolution Fine-Grained Classification
• Data-driven Meta-set Based Fine-Grained Visual Classification
• Compressive Visual Representations
• Effective Domain Knowledge Transfer with Soft Fine-tuning
• Reasoning about Fine-grained Attribute Phrases using Reference Games
• Efficient Multi-Domain Network Learning by Covariance Normalization
• Large-Scale Meta-Learning with Continual Trajectory Shifting
• Sequential Random Network for Fine-grained Image Classification
• Local Patch AutoAugment with Multi-Agent Collaboration
• Defending from adversarial examples with a two-stream architecture
• Automatic Image Labelling at Pixel Level
• Domain-Agnostic Few-Shot Classification by Learning Disparate Modulators
• One to Transfer All: A Universal Transfer Framework for Vision Foundation Model with Few Data
• Compact Approximation for Polynomial of Covariance Feature
• Adversarial AutoMixup
• On the robustness of self-supervised representations for multi-view object classification
• Modular Adaptation for Cross-Domain Few-Shot Learning
• One Representation to Rule Them All: Identifying Out-of-Support Examples in Few-shot Learning with Generic Representations
• Channel DropBlock: An Improved Regularization Method for Fine-Grained Visual Classification
• Fine-Grained Visual Classification via Simultaneously Learning of Multi-regional Multi-grained Features
• Learning a Discriminant Latent Space with Neural Discriminant Analysis
• Automatic Dataset Augmentation
• Resource and data efficient self supervised learning
• Towards Recognizing New Semantic Concepts in New Visual Domains
• Knowledge Transfer Based Fine-grained Visual Classification
• Intrinsic Autoencoders for Joint Neural Rendering and Intrinsic Image Decomposition
• Fuzzy Simplicial Networks: A Topology-Inspired Model to Improve Task Generalization in Few-shot Learning
• Supervised Momentum Contrastive Learning for Few-Shot Classification
• Empirical Performance Analysis of Conventional Deep Learning Models for Recognition of Objects in 2-D Images
• How Well Do Sparse Imagenet Models Transfer?
• Continual Novelty Detection
• ExchNet: A Unified Hashing Network for Large-Scale Fine-Grained Image Retrieval
• DIVA: Dataset Derivative of a Learning Task
• Adaptive Transfer Learning: a simple but effective transfer learning
• Semi-Supervised Learning with Taxonomic Labels
• Volumetric Transformer Networks
• Fine-Grained Categorization via CNN-Based Automatic Extraction and Integration of Object-Level and Part-Level Features
• Learning to Transfer Learn: Reinforcement Learning-Based Selection for Adaptive Transfer Learning
• Affine Non-negative Collaborative Representation Based Pattern Classification
• Spatial-Scale Aligned Network for Fine-Grained Recognition
• Continually Learn to Map Visual Concepts to Large Language Models in Resource-constrained Environments
• Shape Adaptor: A Learnable Resizing Module
• Salvage Reusable Samples from Noisy Data for Robust Learning
• Online Refinement of Low-level Feature Based Activation Map for Weakly Supervised Object Localization
• Cost-Aware Fine-Grained Recognition for IoTs Based on Sequential Fixations
• Searching for TrioNet: Combining Convolution with Local and Global Self-Attention
• Self-Tuning for Data-Efficient Deep Learning
• Interpretable Attention Guided Network for Fine-grained Visual Classification