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 21612170 of 10420 papers

TitleStatusHype
Contrastive Learning of Generalized Game RepresentationsCode1
Learning from Noisy Labels with Decoupled Meta Label PurifierCode1
Continual Learning Using a Kernel-Based Method Over Foundation ModelsCode1
Learning Iterative Reasoning through Energy MinimizationCode1
Data Feedback Loops: Model-driven Amplification of Dataset BiasesCode1
One-Class Risk Estimation for One-Class Hyperspectral Image ClassificationCode1
A General Regret Bound of Preconditioned Gradient Method for DNN TrainingCode1
DataMUX: Data Multiplexing for Neural NetworksCode1
Continual Learning with Scaled Gradient ProjectionCode1
Improving Vision Transformers by Revisiting High-frequency ComponentsCode1
Show:102550
← PrevPage 217 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
5Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2Unverified
6DaViT-HTop 1 Accuracy90.2Unverified
7SwinV2-GTop 1 Accuracy90.17Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05Unverified
10RevCol-HTop 1 Accuracy90Unverified