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 70767100 of 10420 papers

TitleStatusHype
On the Effectiveness of Deep Ensembles for Small Data Tasks0
Function-Space Variational Inference for Deep Bayesian Classification0
On the Effectiveness of Neural Ensembles for Image Classification with Small Datasets0
On the Effectiveness of Regularization Against Membership Inference Attacks0
On the Effects of Different Types of Label Noise in Multi-Label Remote Sensing Image Classification0
Encoding Hierarchical Information in Neural Networks helps in Subpopulation Shift0
On the Eigenvalues of Global Covariance Pooling for Fine-grained Visual Recognition0
Continual Learning with Bayesian Model based on a Fixed Pre-trained Feature Extractor0
On the Evaluation of User Privacy in Deep Neural Networks using Timing Side Channel0
Encoding High Dimensional Local Features by Sparse Coding Based Fisher Vectors0
On the generalization capabilities of FSL methods through domain adaptation: a case study in endoscopic kidney stone image classification0
Function-Space Regularization for Deep Bayesian Classification0
A study of the effect of JPG compression on adversarial images0
Adapted and Oversegmenting Graphs: Application to Geometric Deep Learning0
A Framework for Generalizing Critical Heat Flux Detection Models Using Unsupervised Image-to-Image Translation0
Active Generative Adversarial Network for Image Classification0
On the Importance of Normalisation Layers in Deep Learning with Piecewise Linear Activation Units0
Fully Hyperbolic Convolutional Neural Networks0
An Optimization and Generalization Analysis for Max-Pooling Networks0
Fully Convolutional Neural Networks to Detect Clinical Dermoscopic Features0
On the Initial Behavior Monitoring Issues in Federated Learning0
On the interplay of adversarial robustness and architecture components: patches, convolution and attention0
End-to-End Optimization of JPEG-Based Deep Learning Process for Image Classification0
A Study of Image Analysis with Tangent Distance0
Unsupervised Continual Learning Via Pseudo Labels0
Show:102550
← PrevPage 284 of 417Next →

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
10RevCol-HTop 1 Accuracy90Unverified