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 63266350 of 10420 papers

TitleStatusHype
EMDS-5: Environmental Microorganism Image Dataset Fifth Version for Multiple Image Analysis Tasks0
Neural Sampling Machine with Stochastic Synapse allows Brain-like Learning and Inference0
Hard-Attention for Scalable Image ClassificationCode1
PRICURE: Privacy-Preserving Collaborative Inference in a Multi-Party SettingCode0
Image Classification using CNN for Traffic Signs in Pakistan0
One Shot Model For COVID-19 Classification and Lesions Segmentation In Chest CT Scans Using LSTM With Attention MechanismCode0
Center Smoothing: Certified Robustness for Networks with Structured OutputsCode0
Fortify Machine Learning Production Systems: Detect and Classify Adversarial Attacks0
Adaptive Rational Activations to Boost Deep Reinforcement LearningCode1
Unbiased Teacher for Semi-Supervised Object DetectionCode1
Efficient Online ML API Selection for Multi-Label Classification Tasks0
Centroid Transformers: Learning to Abstract with Attention0
LambdaNetworks: Modeling Long-Range Interactions Without AttentionCode2
Robust Domain-Free Domain Generalization with Class-aware Alignment0
Firefly Neural Architecture Descent: a General Approach for Growing Neural NetworksCode1
DEUP: Direct Epistemic Uncertainty PredictionCode1
Training Stacked Denoising Autoencoders for Representation Learning0
Just Noticeable Difference for Deep Machine Vision0
Adaptive Weighting Scheme for Automatic Time-Series Data Augmentation0
Just Noticeable Difference for Machine Perception and Generation of Regularized Adversarial Images with Minimal Perturbation0
Instance Localization for Self-supervised Detection PretrainingCode1
AlphaNet: Improved Training of Supernets with Alpha-DivergenceCode1
Dataset Condensation with Differentiable Siamese AugmentationCode0
GradInit: Learning to Initialize Neural Networks for Stable and Efficient TrainingCode1
Momentum Residual Neural NetworksCode1
Show:102550
← PrevPage 254 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