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 16511700 of 10419 papers

TitleStatusHype
Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image EncodingCode1
Confidence-aware multi-modality learning for eye disease screeningCode1
Deep Fast Vision: A Python Library for Accelerated Deep Transfer Learning Vision PrototypingCode1
Multimodal Categorization of Crisis Events in Social MediaCode1
Deep Fast Vision: Accelerated Deep Transfer Learning Vision Prototyping and BeyondCode1
Multi-Modal Reasoning Graph for Scene-Text Based Fine-Grained Image Classification and RetrievalCode1
Multi-Objective Interpolation Training for Robustness to Label NoiseCode1
Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image ClassificationCode1
Multiscale Context-Aware Ensemble Deep KELM for Efficient Hyperspectral Image ClassificationCode1
Capsule Network based Contrastive Learning of Unsupervised Visual RepresentationsCode1
Confidence Regularized Self-TrainingCode1
Multi-Scale Dense Networks for Resource Efficient Image ClassificationCode1
Deep Fried ConvnetsCode1
Mutual Contrastive Learning for Visual Representation LearningCode1
Capsules with Inverted Dot-Product Attention RoutingCode1
MUXConv: Information Multiplexing in Convolutional Neural NetworksCode1
Carrying out CNN Channel Pruning in a White BoxCode1
NAS-Bench-360: Benchmarking Neural Architecture Search on Diverse TasksCode1
Navigating the Pitfalls of Active Learning Evaluation: A Systematic Framework for Meaningful Performance AssessmentCode1
Post-Training Piecewise Linear Quantization for Deep Neural NetworksCode1
Deep Learning Based Brain Tumor Segmentation: A SurveyCode1
Deep convolutional tensor networkCode1
Nested Collaborative Learning for Long-Tailed Visual RecognitionCode1
Deep Complex NetworksCode1
Network Adjustment: Channel Search Guided by FLOPs Utilization RatioCode1
Categorical Relation-Preserving Contrastive Knowledge Distillation for Medical Image ClassificationCode1
Neural Architecture Search for Lightweight Non-Local NetworksCode1
Category-Prompt Refined Feature Learning for Long-Tailed Multi-Label Image ClassificationCode1
Deep CORAL: Correlation Alignment for Deep Domain AdaptationCode1
Category-wise Fine-Tuning: Resisting Incorrect Pseudo-Labels in Multi-Label Image Classification with Partial LabelsCode1
Consistency-based Active Learning for Object DetectionCode1
Neural Ensemble Search for Uncertainty Estimation and Dataset ShiftCode1
Deep AutoAugmentCode1
Deep CNNs Meet Global Covariance Pooling: Better Representation and GeneralizationCode1
DeepEMD: Differentiable Earth Mover's Distance for Few-Shot LearningCode1
Noisy Differentiable Architecture SearchCode1
Decoupled Dynamic Filter NetworksCode1
Non-convex Learning via Replica Exchange Stochastic Gradient MCMCCode1
Non-Local Neural Networks With Grouped Bilinear Attentional TransformsCode1
No Parameters Left Behind: Sensitivity Guided Adaptive Learning Rate for Training Large Transformer ModelsCode1
Causal Transportability for Visual RecognitionCode1
Advancing Vision Transformers with Group-Mix AttentionCode1
No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification ProblemsCode1
Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image RecognitionCode1
Decoupled Weight Decay RegularizationCode1
NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture SearchCode1
Astroformer: More Data Might not be all you need for ClassificationCode1
Obtaining Calibrated Probabilities with Personalized Ranking ModelsCode1
Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning ParadigmCode1
Channel Importance Matters in Few-Shot Image ClassificationCode1
Show:102550
← PrevPage 34 of 209Next →

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