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 21262150 of 10420 papers

TitleStatusHype
Combating Label Noise in Deep Learning Using AbstentionCode1
Derivative Manipulation for General Example WeightingCode1
Shredder: Learning Noise Distributions to Protect Inference PrivacyCode1
ProbAct: A Probabilistic Activation Function for Deep Neural NetworksCode1
DIANet: Dense-and-Implicit Attention NetworkCode1
Understanding and Utilizing Deep Neural Networks Trained with Noisy LabelsCode1
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable FeaturesCode1
Learning Loss for Active LearningCode1
AutoAssist: A Framework to Accelerate Training of Deep Neural NetworksCode1
MixMatch: A Holistic Approach to Semi-Supervised LearningCode1
Searching for MobileNetV3Code1
Billion-scale semi-supervised learning for image classificationCode1
Fast AutoAugmentCode1
Harmonic Networks with Limited Training SamplesCode1
Unsupervised Data Augmentation for Consistency TrainingCode1
Transformers with convolutional context for ASRCode1
Making Convolutional Networks Shift-Invariant AgainCode1
Counterfactual Visual ExplanationsCode1
Deep CNNs Meet Global Covariance Pooling: Better Representation and GeneralizationCode1
Weakly Supervised Learning of Instance Segmentation with Inter-pixel RelationsCode1
Hyperbolic Image EmbeddingsCode1
Augmented Neural ODEsCode1
Res2Net: A New Multi-scale Backbone ArchitectureCode1
Variational Adversarial Active LearningCode1
IMAE for Noise-Robust Learning: Mean Absolute Error Does Not Treat Examples Equally and Gradient Magnitude's Variance MattersCode1
Show:102550
← PrevPage 86 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