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 11911200 of 10420 papers

TitleStatusHype
Augmentation-Free Dense Contrastive Knowledge Distillation for Efficient Semantic SegmentationCode1
Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable PrototypesCode1
DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed DatasetsCode1
Augmentation Strategies for Learning with Noisy LabelsCode1
AutoMix: Unveiling the Power of Mixup for Stronger ClassifiersCode1
Demonstrating the Efficacy of Kolmogorov-Arnold Networks in Vision TasksCode1
Benchmarking Pathology Feature Extractors for Whole Slide Image ClassificationCode1
Dendritic Learning-incorporated Vision Transformer for Image RecognitionCode1
Asymmetric Loss For Multi-Label ClassificationCode1
Controllable Orthogonalization in Training DNNsCode1
Show:102550
← PrevPage 120 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