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 36913700 of 10420 papers

TitleStatusHype
AltCLIP: Altering the Language Encoder in CLIP for Extended Language CapabilitiesCode4
Depth and Representation in Vision ModelsCode0
A Comprehensive Survey of Transformers for Computer Vision0
Token Transformer: Can class token help window-based transformer build better long-range interactions?0
Equivariance with Learned Canonicalization Functions0
Dual Complementary Dynamic Convolution for Image Recognition0
REVEL Framework to measure Local Linear Explanations for black-box models: Deep Learning Image Classification case of studyCode0
PAD-Net: An Efficient Framework for Dynamic NetworksCode1
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable ConvolutionsCode4
MGiaD: Multigrid in all dimensions. Efficiency and robustness by coarsening in resolution and channel dimensions0
Show:102550
← PrevPage 370 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