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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 201–250 of 353 papers

TitleStatusHype
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without SupervisionCode0
Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification from the Bottom UpCode0
When Vision Transformers Outperform ResNets without Pre-training or Strong Data AugmentationsCode0
With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual RepresentationsCode0
Fine-Grained Vehicle Classification with Unsupervised Parts Co-occurrence Learning—0
Fine-Grained Sports, Yoga, and Dance Postures Recognition: A Benchmark Analysis—0
Transformer with Peak Suppression and Knowledge Guidance for Fine-grained Image Recognition—0
LLM-based Hierarchical Concept Decomposition for Interpretable Fine-Grained Image Classification—0
Fine-grained Recognition Datasets for Biodiversity Analysis—0
Look Closer to See Better: Recurrent Attention Convolutional Neural Network for Fine-Grained Image Recognition—0
TransIFC: Invariant Cues-aware Feature Concentration Learning for Efficient Fine-grained Bird Image Classification—0
Fine-Grained Recognition as HSnet Search for Informative Image Parts—0
Low-Rank Pairwise Alignment Bilinear Network For Few-Shot Fine-Grained Image Classification—0
Fine-grained Recognition: Accounting for Subtle Differences between Similar Classes—0
Assessing The Importance Of Colours For CNNs In Object Recognition—0
Fine-Grained Image Classification via Combining Vision and Language—0
Maximum-Entropy Fine Grained Classification—0
Maximum-Entropy Fine-Grained Classification—0
Maximum Entropy Regularization and Chinese Text Recognition—0
MedFocusCLIP : Improving few shot classification in medical datasets using pixel wise attention—0
0/1 Deep Neural Networks via Block Coordinate Descent—0
Fine-grained Image Classification by Exploring Bipartite-Graph Labels—0
Fine-Grained Few Shot Learning with Foreground Object Transformation—0
A Spectral Nonlocal Block for Neural Networks—0
Fine-grained Discriminative Localization via Saliency-guided Faster R-CNN—0
Modelling Local Deep Convolutional Neural Network Features to Improve Fine-Grained Image Classification—0
Fine-Grained Classification via Mixture of Deep Convolutional Neural Networks—0
Fine-grained Classification via Categorical Memory Networks—0
Multimodal Semantic Transfer from Text to Image. Fine-Grained Image Classification by Distributional Semantics—0
10,000+ Times Accelerated Robust Subset Selection (ARSS)—0
Where to Focus: Deep Attention-based Spatially Recurrent Bilinear Networks for Fine-Grained Visual Recognition—0
An Erudite Fine-Grained Visual Classification Model—0
Natural World Distribution via Adaptive Confusion Energy Regularization—0
NDPNet: A novel non-linear data projection network for few-shot fine-grained image classification—0
Fine-grained Classification of Solder Joints with α-skew Jensen-Shannon Divergence—0
Fine-graind Image Classification via Combining Vision and Language—0
Nonparametric Part Transfer for Fine-grained Recognition—0
Object-aware Long-short-range Spatial Alignment for Few-Shot Fine-Grained Image Classification—0
Object-centric Sampling for Fine-grained Image Classification—0
Unsupervised Learning using Pretrained CNN and Associative Memory Bank—0
OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning—0
OmniVec: Learning robust representations with cross modal sharing—0
Unsupervised Part Mining for Fine-grained Image Classification—0
On the Ideal Number of Groups for Isometric Gradient Propagation—0
Alignment Enhancement Network for Fine-grained Visual Categorization—0
Zero-Shot Fine-Grained Classification by Deep Feature Learning with Semantics—0
Few-shot Learning for Domain-specific Fine-grained Image Classification—0
Part-based R-CNNs for Fine-grained Category Detection—0
Aligned to the Object, not to the Image: A Unified Pose-aligned Representation for Fine-grained Recognition—0
Feature Channel Adaptive Enhancement for Fine-Grained Visual Classification—0
Show:102550
← PrevPage 5 of 8Next →
All datasetsStanford CarsFGVC-AircraftCUB-200-2011NABirdsOxford 102 FlowersStanford DogsOxford-IIIT PetsCaltech-101Food-101Oxford-IIIT Pet DatasetCompCarsBird-225

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1TResnet-L + PMDAccuracy97.3—Unverified
2CMAL-NetAccuracy97.1—Unverified
3I2-HOFIAccuracy96.92—Unverified
4TResNet-L + ML-DecoderAccuracy96.41—Unverified
5DATAccuracy96.2—Unverified
6ALIGNAccuracy96.13—Unverified
7SR-GNNAccuracy96.1—Unverified
8EffNet-L2 (SAM)Accuracy95.96—Unverified
9SaSPA + CALAccuracy95.72—Unverified
10CAPAccuracy95.7—Unverified
#ModelMetricClaimedVerifiedStatus
1I2-HOFIAccuracy96.42—Unverified
2SR-GNNAccuracy95.4—Unverified
3Inceptionv4Accuracy95.11—Unverified
4CAPAccuracy94.9—Unverified
5CSQA-NetAccuracy94.7—Unverified
6CMAL-NetAccuracy94.7—Unverified
7TBMSL-NetAccuracy94.7—Unverified
8PARTAccuracy94.6—Unverified
9SaSPA + CALAccuracy94.5—Unverified
10AENetAccuracy94.5—Unverified
#ModelMetricClaimedVerifiedStatus
1HERBSAccuracy93.1—Unverified
2PIMAccuracy92.8—Unverified
3MDCMAccuracy92.5—Unverified
4IELTAccuracy91.8—Unverified
5CAPAccuracy91.8—Unverified
6SFETransAccuracy91.8—Unverified
7SWAG (ViT H/14)Accuracy91.7—Unverified
8ViT-NeTAccuracy91.7—Unverified
9TransFGAccuracy91.7—Unverified
10I2-HOFIAccuracy91.6—Unverified
#ModelMetricClaimedVerifiedStatus
1HERBSAccuracy93—Unverified
2MetaFormer (MetaFormer-2,384)Accuracy93—Unverified
3PIMAccuracy92.8—Unverified
4MPSAAccuracy92.5—Unverified
5ViT-NeT (SwinV2-B)Accuracy92.5—Unverified
6CSQA-NetAccuracy92.3—Unverified
7I2-HOFIAccuracy92.12—Unverified
8MDCMAccuracy92—Unverified
9CGLAccuracy91.7—Unverified
10SR-GNNAccuracy91.2—Unverified