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 17611770 of 10420 papers

TitleStatusHype
Circumventing Outliers of AutoAugment with Knowledge DistillationCode1
PolyLoss: A Polynomial Expansion Perspective of Classification Loss FunctionsCode1
Post-hoc Uncertainty Learning using a Dirichlet Meta-ModelCode1
POUF: Prompt-oriented unsupervised fine-tuning for large pre-trained modelsCode1
Deep Fast Vision: Accelerated Deep Transfer Learning Vision Prototyping and BeyondCode1
Practical No-box Adversarial Attacks against DNNsCode1
Class Adaptive Network CalibrationCode1
Presence-Only Geographical Priors for Fine-Grained Image ClassificationCode1
Pretrained ViTs Yield Versatile Representations For Medical ImagesCode1
DeepEMD: Differentiable Earth Mover's Distance for Few-Shot LearningCode1
Show:102550
← PrevPage 177 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