SOTAVerified

Fine-Grained Image Classification

Fine-Grained Image Classification is a task in computer vision where the goal is to classify images into subcategories within a larger category. For example, classifying different species of birds or different types of flowers. This task is considered to be fine-grained because it requires the model to distinguish between subtle differences in visual appearance and patterns, making it more challenging than regular image classification tasks.

( Image credit: Looking for the Devil in the Details )

Papers

Showing 51100 of 353 papers

TitleStatusHype
Context-aware Attentional Pooling (CAP) for Fine-grained Visual ClassificationCode1
Proxy Anchor Loss for Deep Metric LearningCode1
TOAST: Transfer Learning via Attention SteeringCode1
Contrastive Deep SupervisionCode1
Roll With the Punches: Expansion and Shrinkage of Soft Label Selection for Semi-supervised Fine-Grained LearningCode1
2nd Place Solution to Google Universal Image EmbeddingCode1
ImageNet-21K Pretraining for the MassesCode1
Image Difference Captioning with Pre-training and Contrastive LearningCode1
Improved Zero-Shot Classification by Adapting VLMs with Text DescriptionsCode1
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identificationCode1
Self-Supervised Learning for Fine-Grained Image ClassificationCode1
A Comprehensive Study on Torchvision Pre-trained Models for Fine-grained Inter-species ClassificationCode1
Feature Boosting, Suppression, and Diversification for Fine-Grained Visual ClassificationCode1
Gradient Centralization: A New Optimization Technique for Deep Neural NetworksCode1
Knowledge Mining with Scene Text for Fine-Grained RecognitionCode1
Dataset Condensation with Contrastive SignalsCode1
Focus Longer to See Better:Recursively Refined Attention for Fine-Grained Image ClassificationCode1
Exploration of Class Center for Fine-Grained Visual ClassificationCode1
Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine SynergyCode1
Fine-grained Visual Classification with High-temperature Refinement and Background SuppressionCode1
Bi-directional Feature Reconstruction Network for Fine-Grained Few-Shot Image ClassificationCode1
Exploring Vision Transformers for Fine-grained ClassificationCode1
GIST: Generating Image-Specific Text for Fine-grained Object ClassificationCode1
Good Questions Help Zero-Shot Image ReasoningCode1
Danish Fungi 2020 -- Not Just Another Image Recognition DatasetCode1
Human Attention in Fine-grained ClassificationCode1
BirdSAT: Cross-View Contrastive Masked Autoencoders for Bird Species Classification and MappingCode1
DenoiseRep: Denoising Model for Representation LearningCode1
Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw PatchesCode1
Fine-Grained Visual Classification via Simultaneously Learning of Multi-regional Multi-grained FeaturesCode1
BSNet: Bi-Similarity Network for Few-shot Fine-grained Image ClassificationCode1
Diffusion Models Beat GANs on Image ClassificationCode1
Escaping the Big Data Paradigm with Compact TransformersCode1
Advancing Fine-Grained Classification by Structure and Subject Preserving AugmentationCode1
Learn from Each Other to Classify Better: Cross-layer Mutual Attention Learning for Fine-grained Visual ClassificationCode1
Learning Attentive Pairwise Interaction for Fine-Grained ClassificationCode1
A Simple Interpretable Transformer for Fine-Grained Image Classification and AnalysisCode1
Learning to Navigate for Fine-grained ClassificationCode1
Look-into-Object: Self-supervised Structure Modeling for Object RecognitionCode1
Making a Bird AI Expert Work for You and MeCode1
Dynamic MLP for Fine-Grained Image Classification by Leveraging Geographical and Temporal InformationCode1
Fine-Grained Visual Classification using Self Assessment ClassifierCode1
Fine-Grained Visual Classification via Internal Ensemble Learning TransformerCode1
ML-Decoder: Scalable and Versatile Classification HeadCode1
Generative Parameter-Efficient Fine-TuningCode1
Fine-grained Image Classification and Retrieval by Combining Visual and Locally Pooled Textual FeaturesCode1
Part-guided Relational Transformers for Fine-grained Visual RecognitionCode1
PDiscoFormer: Relaxing Part Discovery Constraints with Vision TransformersCode1
Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural NetworkCode1
Label Relation Graphs Enhanced Hierarchical Residual Network for Hierarchical Multi-Granularity ClassificationCode1
Show:102550
← PrevPage 2 of 8Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1TResnet-L + PMDAccuracy97.3Unverified
2CMAL-NetAccuracy97.1Unverified
3I2-HOFIAccuracy96.92Unverified
4TResNet-L + ML-DecoderAccuracy96.41Unverified
5DATAccuracy96.2Unverified
6ALIGNAccuracy96.13Unverified
7SR-GNNAccuracy96.1Unverified
8EffNet-L2 (SAM)Accuracy95.96Unverified
9SaSPA + CALAccuracy95.72Unverified
10CAPAccuracy95.7Unverified
#ModelMetricClaimedVerifiedStatus
1I2-HOFIAccuracy96.42Unverified
2SR-GNNAccuracy95.4Unverified
3Inceptionv4Accuracy95.11Unverified
4CAPAccuracy94.9Unverified
5CSQA-NetAccuracy94.7Unverified
6CMAL-NetAccuracy94.7Unverified
7TBMSL-NetAccuracy94.7Unverified
8PARTAccuracy94.6Unverified
9SaSPA + CALAccuracy94.5Unverified
10AENetAccuracy94.5Unverified
#ModelMetricClaimedVerifiedStatus
1HERBSAccuracy93.1Unverified
2PIMAccuracy92.8Unverified
3MDCMAccuracy92.5Unverified
4IELTAccuracy91.8Unverified
5CAPAccuracy91.8Unverified
6SFETransAccuracy91.8Unverified
7TransFGAccuracy91.7Unverified
8ViT-NeTAccuracy91.7Unverified
9SWAG (ViT H/14)Accuracy91.7Unverified
10FFVTAccuracy91.6Unverified
#ModelMetricClaimedVerifiedStatus
1MetaFormer (MetaFormer-2,384)Accuracy93Unverified
2HERBSAccuracy93Unverified
3PIMAccuracy92.8Unverified
4ViT-NeT (SwinV2-B)Accuracy92.5Unverified
5MPSAAccuracy92.5Unverified
6CSQA-NetAccuracy92.3Unverified
7I2-HOFIAccuracy92.12Unverified
8MDCMAccuracy92Unverified
9CGLAccuracy91.7Unverified
10SR-GNNAccuracy91.2Unverified