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 18261850 of 10420 papers

TitleStatusHype
Scalable Penalized Regression for Noise Detection in Learning with Noisy LabelsCode1
Combining Human Predictions with Model Probabilities via Confusion Matrices and CalibrationCode1
FC-KAN: Function Combinations in Kolmogorov-Arnold NetworksCode1
FDFtNet: Facing Off Fake Images using Fake Detection Fine-tuning NetworkCode1
Scaling Graph Convolutions for Mobile VisionCode1
Go Wider Instead of DeeperCode1
GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group PropagationCode1
GlobalMamba: Global Image Serialization for Vision MambaCode1
Feature Guided Masked Autoencoder for Self-supervised Learning in Remote SensingCode1
A Fuzzy Rank-based Ensemble of CNN Models for Classification of Cervical CytologyCode1
FedBABU: Towards Enhanced Representation for Federated Image ClassificationCode1
CLCC: Contrastive Learning for Color ConstancyCode1
CLCNet: Rethinking of Ensemble Modeling with Classification Confidence NetworkCode1
Federated Learning via Input-Output Collaborative DistillationCode1
Clean-Label Backdoor Attacks on Video Recognition ModelsCode1
CleanNet: Transfer Learning for Scalable Image Classifier Training with Label NoiseCode1
Schema Inference for Interpretable Image ClassificationCode1
Adversarial Examples in Deep Learning for Multivariate Time Series RegressionCode1
Federated Model Aggregation via Self-Supervised Priors for Highly Imbalanced Medical Image ClassificationCode1
Going Beyond One-Hot Encoding in Classification: Can Human Uncertainty Improve Model Performance?Code1
CLIP4IDC: CLIP for Image Difference CaptioningCode1
A Comprehensive Survey on Graph Neural NetworksCode1
A fuzzy distance-based ensemble of deep models for cervical cancer detectionCode1
FedMLP: Federated Multi-Label Medical Image Classification under Task HeterogeneityCode1
Global Filter Networks for Image ClassificationCode1
Show:102550
← PrevPage 74 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
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