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 28812890 of 10420 papers

TitleStatusHype
Exploring Emerging Trends and Research Opportunities in Visual Place Recognition0
Diagnostic Text-guided Representation Learning in Hierarchical Classification for Pathological Whole Slide Image0
Multi-perspective Contrastive Logit Distillation0
Deep Feature Response Discriminative CalibrationCode0
Hysteresis Activation Function for Efficient InferenceCode0
On the Cost of Model-Serving Frameworks: An Experimental Evaluation0
Embedding Byzantine Fault Tolerance into Federated Learning via Virtual Data-Driven Consistency Scoring PluginCode0
Evidential Federated Learning for Skin Lesion Image Classification0
Adapting the Biological SSVEP Response to Artificial Neural Networks0
Outliers resistant image classification by anomaly detection0
Show:102550
← PrevPage 289 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