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 22312240 of 10420 papers

TitleStatusHype
Aggregated Residual Transformations for Deep Neural NetworksCode1
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based LocalizationCode1
Densely Connected Convolutional NetworksCode1
Deep CORAL: Correlation Alignment for Deep Domain AdaptationCode1
Explaining Predictions of Non-Linear Classifiers in NLPCode1
Wide Residual NetworksCode1
Deep Networks with Stochastic DepthCode1
Identity Mappings in Deep Residual NetworksCode1
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizeCode1
Inception-v4, Inception-ResNet and the Impact of Residual Connections on LearningCode1
Show:102550
← PrevPage 224 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