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 86268650 of 10420 papers

TitleStatusHype
Local Relation Networks for Image RecognitionCode0
Low-Memory Neural Network Training: A Technical Report0
Plug-in, Trainable Gate for Streamlining Arbitrary Neural Networks0
Deep Sparse Representation-based ClassificationCode0
Detecting inter-sectional accuracy differences in driver drowsiness detection algorithms0
DenseNet Models for Tiny ImageNet ClassificationCode0
Attention Augmented Convolutional NetworksCode0
Switchable Whitening for Deep Representation LearningCode0
State Classification of Cooking Objects Using a VGG CNN0
Neural Architecture Search for Deep Face Recognition0
Data-Driven Neuron Allocation for Scale Aggregation NetworksCode0
Class specific or shared? A cascaded dictionary learning framework for image classification0
A large-scale field test on word-image classification in large historical document collections using a traditional and two deep-learning methods0
Correlated Logistic Model With Elastic Net Regularization for Multilabel Image Classification0
TextCaps : Handwritten Character Recognition with Very Small DatasetsCode0
Sparseout: Controlling Sparsity in Deep NetworksCode0
Deep learning for image segmentation: veritable or overhyped?0
Cryo-Electron Microscopy Image Analysis Using Multi-Frequency Vector Diffusion Maps0
Double Transfer Learning for Breast Cancer Histopathologic Image Classification0
Counterfactual Visual ExplanationsCode1
Deep Neural Network Based Hyperspectral Pixel Classification With Factorized Spectral-Spatial Feature Representation0
Deep CNNs Meet Global Covariance Pooling: Better Representation and GeneralizationCode1
LeanResNet: A Low-cost Yet Effective Convolutional Residual Networks0
Texture image analysis and texture classification methods - A review0
Incremental multi-domain learning with network latent tensor factorization0
Show:102550
← PrevPage 346 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