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 35313540 of 10420 papers

TitleStatusHype
Bayesian posterior approximation with stochastic ensemblesCode0
Backdoor Attack Detection in Computer Vision by Applying Matrix Factorization on the Weights of Deep Networks0
Learning to Detect Semantic Boundaries with Image-level Class Labels0
CLIPPO: Image-and-Language Understanding from Pixels Only0
Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and LanguageCode1
SAIF: Sparse Adversarial and Imperceptible Attack Framework0
Reproducible scaling laws for contrastive language-image learningCode1
Domain Generalization by Learning and Removing Domain-specific FeaturesCode1
Design-time Fashion Popularity Forecasting in VR Environments0
Post-hoc Uncertainty Learning using a Dirichlet Meta-ModelCode1
Show:102550
← PrevPage 354 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