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 110 of 353 papers

TitleStatusHype
Hierarchical Mask-Enhanced Dual Reconstruction Network for Few-Shot Fine-Grained Image ClassificationCode0
Structural feature enhanced transformer for fine-grained image recognition0
GPLQ: A General, Practical, and Lightning QAT Method for Vision Transformers0
Towards Privacy-Preserving Fine-Grained Visual Classification via Hierarchical Learning from Label Proportions0
DS_FusionNet: Dynamic Dual-Stream Fusion with Bidirectional Knowledge Distillation for Plant Disease RecognitionCode0
Enhancing Multimodal In-Context Learning for Image Classification through Coreset Optimization0
Cross-Hierarchical Bidirectional Consistency Learning for Fine-Grained Visual Classification0
Adaptive Classification of Interval-Valued Time Series0
Visual-RFT: Visual Reinforcement Fine-TuningCode7
An Attention-Locating Algorithm for Eliminating Background Effects in Fine-grained Visual ClassificationCode0
Show:102550
← PrevPage 1 of 36Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1EffNet-L2 (SAM)Accuracy97.1Unverified
2BiT-L (ResNet)Accuracy96.62Unverified
3µ2Net+ (ViT-L/16)Accuracy95.5Unverified
4µ2Net (ViT-L/16)Accuracy95.3Unverified
5BiT-M (ResNet)Accuracy94.47Unverified
6Assemble-ResNet-FGVC-50Accuracy94.3Unverified
7NAT-M4Accuracy94.3Unverified
8NAT-M3Accuracy94.1Unverified
9NAT-M2Accuracy93.5Unverified
10ResNet-152-SAMAccuracy93.3Unverified