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 33213330 of 10420 papers

TitleStatusHype
Improving (α, f)-Byzantine Resilience in Federated Learning via layerwise aggregation and cosine distanceCode0
Dynamic Mode Decomposition based feature for Image ClassificationCode0
Improving Confident-Classifiers For Out-of-distribution DetectionCode0
Improving Ensemble Distillation With Weight Averaging and Diversifying PerturbationCode0
Deep Learning with Gaussian Differential PrivacyCode0
Deep learning with Elastic Averaging SGDCode0
Deep Learning with Eigenvalue Decay RegularizerCode0
Deep Learning using Linear Support Vector MachinesCode0
Balanced Mixture of SuperNets for Learning the CNN Pooling ArchitectureCode0
AmsterTime: A Visual Place Recognition Benchmark Dataset for Severe Domain ShiftCode0
Show:102550
← PrevPage 333 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