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 81768200 of 10420 papers

TitleStatusHype
RepAct: The Re-parameterizable Adaptive Activation FunctionCode0
ReNet: A Recurrent Neural Network Based Alternative to Convolutional NetworksCode0
Removing the Feature Correlation Effect of Multiplicative NoiseCode0
Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGradCode0
RemoteTrimmer: Adaptive Structural Pruning for Remote Sensing Image ClassificationCode0
Fast Neural Network Adaptation via Parameter Remapping and Architecture SearchCode0
Fast Low-rank Shared Dictionary Learning for Image ClassificationCode0
Comparative Evaluation of Clustered Federated Learning MethodsCode0
ARIA: On the Interaction Between Architectures, Initialization and Aggregation Methods for Federated Visual ClassificationCode0
Arguing Machines: Human Supervision of Black Box AI Systems That Make Life-Critical DecisionsCode0
A Baseline for Multi-Label Image Classification Using An Ensemble of Deep Convolutional Neural NetworksCode0
ReMarNet: Conjoint Relation and Margin Learning for Small-Sample Image ClassificationCode0
Fast Gradient Descent Algorithm for Image Classification with Neural NetworksCode0
Adversarial Explanations for Understanding Image Classification Decisions and Improved Neural Network RobustnessCode0
Reliability Does Matter: An End-to-End Weakly Supervised Semantic Segmentation ApproachCode0
Comparative Analysis of ImageNet Pre-Trained Deep Learning Models and DINOv2 in Medical Imaging ClassificationCode0
Relative stability toward diffeomorphisms indicates performance in deep netsCode0
Relation Network for Multi-label Aerial Image ClassificationCode0
Relation-Aware Global Attention for Person Re-identificationCode0
Relational Concept Bottleneck ModelsCode0
Frequency maps reveal the correlation between Adversarial Attacks and Implicit BiasCode0
Fast Ensemble Learning Using Adversarially-Generated Restricted Boltzmann MachinesCode0
Fast Dynamic Routing Based on Weighted Kernel Density EstimationCode0
CompactNet: Platform-Aware Automatic Optimization for Convolutional Neural NetworksCode0
Compact Global Descriptor for Neural NetworksCode0
Show:102550
← PrevPage 328 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
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90Unverified