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 85268550 of 10420 papers

TitleStatusHype
Enhanced Meta Label Correction for Coping with Label CorruptionCode0
Enhanced Long-Tailed Recognition with Contrastive CutMix AugmentationCode0
EnGraf-Net: Multiple Granularity Branch Network with Fine-Coarse Graft Grained for Classification TaskCode0
Maximizing Invariant Data Perturbation with Stochastic OptimizationCode0
AutoGAN: Neural Architecture Search for Generative Adversarial NetworksCode0
Continual Learning of Unsupervised Monocular Depth from VideosCode0
Opening Deep Neural Networks with Generative ModelsCode0
End-to-End Supervised Multilabel Contrastive LearningCode0
Revisiting the Calibration of Modern Neural NetworksCode0
EncodingNet: A Novel Encoding-based MAC Design for Efficient Neural Network AccelerationCode0
Maxout NetworksCode0
Continual Learning in Open-vocabulary Classification with Complementary Memory SystemsCode0
Continual Contrastive Learning for Image ClassificationCode0
EnAET: A Self-Trained framework for Semi-Supervised and Supervised Learning with Ensemble TransformationsCode0
MaxUp: A Simple Way to Improve Generalization of Neural Network TrainingCode0
Employing Sentence Space Embedding for Classification of Data Stream from Fake News DomainCode0
Robustness and Overfitting Behavior of Implicit Background ModelsCode0
Continual and Multi-Task Architecture SearchCode0
Empirically Measuring Concentration: Fundamental Limits on Intrinsic RobustnessCode0
AutoFCL: Automatically Tuning Fully Connected Layers for Handling Small DatasetCode0
Empirical Evaluation of Rectified Activations in Convolutional NetworkCode0
Open Set Domain Adaptation for Image and Action RecognitionCode0
Calibrated Top-1 Uncertainty estimates for classification by score based modelsCode0
MCA: Moment Channel Attention NetworksCode0
EMNIST: an extension of MNIST to handwritten lettersCode0
Show:102550
← PrevPage 342 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