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 801825 of 10419 papers

TitleStatusHype
CellGAN: Conditional Cervical Cell Synthesis for Augmenting Cytopathological Image ClassificationCode1
Capsules with Inverted Dot-Product Attention RoutingCode1
EPSANet: An Efficient Pyramid Squeeze Attention Block on Convolutional Neural NetworkCode1
Equivariance-bridged SO(2)-Invariant Representation Learning using Graph Convolutional NetworkCode1
Error-Bounded Correction of Noisy LabelsCode1
Almost-Orthogonal Layers for Efficient General-Purpose Lipschitz NetworksCode1
Deep Roto-Translation Scattering for Object ClassificationCode1
TransCenter: Transformers with Dense Representations for Multiple-Object TrackingCode1
All you need is a good initCode1
Categorical Relation-Preserving Contrastive Knowledge Distillation for Medical Image ClassificationCode1
Category-Prompt Refined Feature Learning for Long-Tailed Multi-Label Image ClassificationCode1
Category Query Learning for Human-Object Interaction ClassificationCode1
Can An Image Classifier Suffice For Action Recognition?Code1
Evaluating the Adversarial Robustness of Adaptive Test-time DefensesCode1
Deep Prototypical Networks with Hybrid Residual Attention for Hyperspectral Image ClassificationCode1
Causal Transportability for Visual RecognitionCode1
Deep Reinforcement Learning for Band Selection in Hyperspectral Image ClassificationCode1
3D U^2-Net: A 3D Universal U-Net for Multi-Domain Medical Image SegmentationCode1
Evolving Normalization-Activation LayersCode1
Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision TransformerCode1
AutoDiCE: Fully Automated Distributed CNN Inference at the EdgeCode1
An In-depth Study of Stochastic BackpropagationCode1
A Dual-Direction Attention Mixed Feature Network for Facial Expression RecognitionCode1
Explainable Deep Learning Methods in Medical Image Classification: A SurveyCode1
Adaptive and Background-Aware Vision Transformer for Real-Time UAV TrackingCode1
Show:102550
← PrevPage 33 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