SOTAVerified

Image Classification

Image Classification is a fundamental task in vision recognition that aims to understand and categorize an image as a whole under a specific label. Unlike object detection, which involves classification and location of multiple objects within an image, image classification typically pertains to single-object images. When the classification becomes highly detailed or reaches instance-level, it is often referred to as image retrieval, which also involves finding similar images in a large database.

Source: Metamorphic Testing for Object Detection Systems

Papers

Showing 32713280 of 10420 papers

TitleStatusHype
Android Malware Detection Based on RGB Images and Multi-feature Fusion0
Dual-branch PolSAR Image Classification Based on GraphMAE and Local Feature Extraction0
Exploring the Deep Feature Space of a Cell Classification Neural Network0
BIRD: Behavior Induction via Representation-structure Distillation0
Higher Chest X-ray Resolution Improves Classification Performance0
Dual Classification Head Self-training Network for Cross-scene Hyperspectral Image Classification0
Dual Complementary Dynamic Convolution for Image Recognition0
Differential Privacy Mechanisms in Neural Tangent Kernel Regression0
Dual-Individual Genetic Algorithm: A Dual-Individual Approach for Efficient Training of Multi-Layer Neural Networks0
A Closer Look at Prototype Classifier for Few-shot Image Classification0
Show:102550
← PrevPage 328 of 1042Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CoCa (finetuned)Top 1 Accuracy91Unverified
2Model soups (BASIC-L)Top 1 Accuracy90.98Unverified
3Model soups (ViT-G/14)Top 1 Accuracy90.94Unverified
4DaViT-GTop 1 Accuracy90.4Unverified
5DaViT-HTop 1 Accuracy90.2Unverified
6Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2Unverified
7SwinV2-GTop 1 Accuracy90.17Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05Unverified
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90Unverified