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 1022610250 of 10420 papers

TitleStatusHype
Regularizing with Pseudo-Negatives for Continual Self-Supervised LearningCode0
CondConv: Conditionally Parameterized Convolutions for Efficient InferenceCode0
Which Backbone to Use: A Resource-efficient Domain Specific Comparison for Computer VisionCode0
SoDeep: a Sorting Deep net to learn ranking loss surrogatesCode0
ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute ModelsCode0
Which Has Better Visual Quality: The Clear Blue Sky or a Blurry Animal?Code0
Xception: Deep Learning with Depthwise Separable ConvolutionsCode0
Matrix Shuffle-Exchange Networks for Hard 2D TasksCode0
Switchable Whitening for Deep Representation LearningCode0
Scissorhands: Scrub Data Influence via Connection Sensitivity in NetworksCode0
V-EfficientNets: Vector-Valued Efficiently Scaled Convolutional Neural Network ModelsCode0
SwGridNet: A Deep Convolutional Neural Network based on Grid Topology for Image ClassificationCode0
Swapped Logit Distillation via Bi-level Teacher AlignmentCode0
SCIDA: Self-Correction Integrated Domain Adaptation from Single- to Multi-label Aerial ImagesCode0
Self-Supervised Learning from Non-Object Centric Images with a Geometric Transformation Sensitive ArchitectureCode0
Verifiably Robust Conformal PredictionCode0
SODAWideNet++: Combining Attention and Convolutions for Salient Object DetectionCode0
SUT: a new multi-purpose synthetic dataset for Farsi document image analysisCode0
Survey: Image Mixing and Deleting for Data AugmentationCode0
Xception: Deep Learning With Depthwise Separable ConvolutionsCode0
Scale-Preserving Automatic Concept Extraction (SPACE)Code0
Triangle Generative Adversarial NetworksCode0
Supervised Infinite Feature SelectionCode0
Who's a Good Boy? Reinforcing Canine Behavior in Real-Time using Machine LearningCode0
Self-supervised learning for skin cancer diagnosis with limited training dataCode0
Show:102550
← PrevPage 410 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