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 31313140 of 10420 papers

TitleStatusHype
Rethinking Local Perception in Lightweight Vision TransformerCode1
DIME-FM: DIstilling Multimodal and Efficient Foundation Models0
LaCViT: A Label-aware Contrastive Fine-tuning Framework for Vision TransformersCode0
Benchmarking FedAvg and FedCurv for Image Classification Tasks0
PMatch: Paired Masked Image Modeling for Dense Geometric MatchingCode1
Mole Recruitment: Poisoning of Image Classifiers via Selective Batch SamplingCode0
Soft Neighbors are Positive Supporters in Contrastive Visual Representation Learning0
Towards Understanding the Effect of Pretraining Label Granularity0
InceptionNeXt: When Inception Meets ConvNeXtCode4
Beyond Empirical Risk Minimization: Local Structure Preserving Regularization for Improving Adversarial Robustness0
Show:102550
← PrevPage 314 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