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 13611370 of 10420 papers

TitleStatusHype
On the Importance of Firth Bias Reduction in Few-Shot ClassificationCode1
Deep Transfer Learning for Land Use and Land Cover Classification: A Comparative StudyCode1
ResNet strikes back: An improved training procedure in timmCode1
Learning Compact Representations of Neural Networks using DiscriminAtive Masking (DAM)Code1
TyXe: Pyro-based Bayesian neural nets for PytorchCode1
Combining Human Predictions with Model Probabilities via Confusion Matrices and CalibrationCode1
NASViT: Neural Architecture Search for Efficient Vision Transformers with Gradient Conflict aware Supernet TrainingCode1
WaveMix: Multi-Resolution Token Mixing for ImagesCode1
Second-Order Neural ODE OptimizerCode1
Evaluation of Deep Neural Network Domain Adaptation Techniques for Image RecognitionCode1
Show:102550
← PrevPage 137 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