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 20762100 of 10420 papers

TitleStatusHype
Depth Uncertainty in Neural NetworksCode1
Anytime Dense Prediction with Confidence AdaptivityCode1
Designing Network Design SpacesCode1
Dense Contrastive Learning for Self-Supervised Visual Pre-TrainingCode1
A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data AugmentationCode1
A Single Graph Convolution Is All You Need: Efficient Grayscale Image ClassificationCode1
DIANet: Dense-and-Implicit Attention NetworkCode1
Container: Context Aggregation NetworkCode1
Differentiable Model Scaling using Differentiable TopkCode1
Differentially Private Synthetic Medical Data Generation using Convolutional GANsCode1
Confidence Regularized Self-TrainingCode1
Content-aware Token Sharing for Efficient Semantic Segmentation with Vision TransformersCode1
Diffusion Model as Representation LearnerCode1
Diffusion Visual Counterfactual ExplanationsCode1
Conformer: Local Features Coupling Global Representations for Visual RecognitionCode1
Densely Connected Convolutional NetworksCode1
A Simple Baseline for Low-Budget Active LearningCode1
Direct Differentiable Augmentation SearchCode1
Directional Statistics-based Deep Metric Learning for Image Classification and RetrievalCode1
DISCO: Adversarial Defense with Local Implicit FunctionsCode1
Discretization-Aware Architecture SearchCode1
Discriminator-free Unsupervised Domain Adaptation for Multi-label Image ClassificationCode1
Disentangle and Remerge: Interventional Knowledge Distillation for Few-Shot Object Detection from A Conditional Causal PerspectiveCode1
Disentangling Label Distribution for Long-tailed Visual RecognitionCode1
CondenseNet V2: Sparse Feature Reactivation for Deep NetworksCode1
Show:102550
← PrevPage 84 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