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 201210 of 10419 papers

TitleStatusHype
MogaNet: Multi-order Gated Aggregation NetworkCode2
WITT: A Wireless Image Transmission Transformer for Semantic CommunicationsCode2
CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View CompletionCode2
The Equalization Losses: Gradient-Driven Training for Long-tailed Object RecognitionCode2
MobileViTv3: Mobile-Friendly Vision Transformer with Simple and Effective Fusion of Local, Global and Input FeaturesCode2
Spikformer: When Spiking Neural Network Meets TransformerCode2
Dilated Neighborhood Attention TransformerCode2
Generalized Parametric Contrastive LearningCode2
HiFuse: Hierarchical Multi-Scale Feature Fusion Network for Medical Image ClassificationCode2
Mega: Moving Average Equipped Gated AttentionCode2
Show:102550
← PrevPage 21 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