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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 776–800 of 10419 papers

TitleStatusHype
Distribution Alignment: A Unified Framework for Long-tail Visual RecognitionCode1
Layer-adaptive sparsity for the Magnitude-based PruningCode1
An Enhanced Scheme for Reducing the Complexity of Pointwise Convolutions in CNNs for Image Classification Based on Interleaved Grouped Filters without Divisibility ConstraintsCode1
Diverse Sample Generation: Pushing the Limit of Generative Data-free QuantizationCode1
Diversified in-domain synthesis with efficient fine-tuning for few-shot classificationCode1
An Ensemble of Simple Convolutional Neural Network Models for MNIST Digit RecognitionCode1
DivideMix: Learning with Noisy Labels as Semi-supervised LearningCode1
CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image ClassificationCode1
Adaptive Checkpoint Adjoint Method for Gradient Estimation in Neural ODECode1
A Neural Dirichlet Process Mixture Model for Task-Free Continual LearningCode1
DocXClassifier: High Performance Explainable Deep Network for Document Image ClassificationCode1
A Less Biased Evaluation of Out-of-distribution Sample DetectorsCode1
Do Input Gradients Highlight Discriminative Features?Code1
Domain-Adversarial Training of Neural NetworksCode1
Domain Generalization by Learning and Removing Domain-specific FeaturesCode1
3D Human Pose Estimation with Spatial and Temporal TransformersCode1
Arch-Net: Model Distillation for Architecture Agnostic Model DeploymentCode1
A New Benchmark: On the Utility of Synthetic Data with Blender for Bare Supervised Learning and Downstream Domain AdaptationCode1
Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse TrainingCode1
Do You Even Need Attention? A Stack of Feed-Forward Layers Does Surprisingly Well on ImageNetCode1
DPMLBench: Holistic Evaluation of Differentially Private Machine LearningCode1
Drastically Reducing the Number of Trainable Parameters in Deep CNNs by Inter-layer Kernel-sharingCode1
DR-Tune: Improving Fine-tuning of Pretrained Visual Models by Distribution Regularization with Semantic CalibrationCode1
Almost-Orthogonal Layers for Efficient General-Purpose Lipschitz NetworksCode1
CLR: Channel-wise Lightweight Reprogramming for Continual LearningCode1
Show:102550
← PrevPage 32 of 417Next →
All datasetsImageNetCIFAR-10CIFAR-100STL-10ObjectNetMNISTSVHNiNaturalist 2018ImageNet ReaLFlowers-102Clothing1Mmini WebVision 1.0

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CoCa (finetuned)Top 1 Accuracy91—Unverified
2Model soups (BASIC-L)Top 1 Accuracy90.98—Unverified
3Model soups (ViT-G/14)Top 1 Accuracy90.94—Unverified
4DaViT-GTop 1 Accuracy90.4—Unverified
5DaViT-HTop 1 Accuracy90.2—Unverified
6Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2—Unverified
7SwinV2-GTop 1 Accuracy90.17—Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1—Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05—Unverified
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90—Unverified