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 751800 of 10419 papers

TitleStatusHype
Learning Semi-supervised Gaussian Mixture Models for Generalized Category DiscoveryCode1
DPMLBench: Holistic Evaluation of Differentially Private Machine LearningCode1
Towards Effective Visual Representations for Partial-Label LearningCode1
DC3DCD: unsupervised learning for multiclass 3D point cloud change detectionCode1
CAMIL: Context-Aware Multiple Instance Learning for Cancer Detection and Subtyping in Whole Slide ImagesCode1
Reduction of Class Activation Uncertainty with Background InformationCode1
Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth LabelsCode1
CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual RepresentationsCode1
POUF: Prompt-oriented unsupervised fine-tuning for large pre-trained modelsCode1
Multistage Relation Network With Dual-Metric for Few-Shot Hyperspectral Image ClassificationCode1
From Association to Generation: Text-only Captioning by Unsupervised Cross-modal MappingCode1
ESPT: A Self-Supervised Episodic Spatial Pretext Task for Improving Few-Shot LearningCode1
Deep Fast Vision: Accelerated Deep Transfer Learning Vision Prototyping and BeyondCode1
Bayesian Optimization Meets Self-DistillationCode1
MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision TransformerCode1
AwesomeMeta+: A Mixed-Prototyping Meta-Learning System Supporting AI Application Design AnywhereCode1
Function-Consistent Feature DistillationCode1
Learning Partial Correlation based Deep Visual Representation for Image ClassificationCode1
Learning Bottleneck Concepts in Image ClassificationCode1
DCN-T: Dual Context Network with Transformer for Hyperspectral Image ClassificationCode1
Hyperbolic Image-Text RepresentationsCode1
TransHP: Image Classification with Hierarchical PromptingCode1
Remote Sensing Change Detection With Transformers Trained from ScratchCode1
Boosting Convolutional Neural Networks with Middle Spectrum Grouped ConvolutionCode1
SpectralDiff: A Generative Framework for Hyperspectral Image Classification with Diffusion ModelsCode1
Towards Evaluating Explanations of Vision Transformers for Medical ImagingCode1
CamDiff: Camouflage Image Augmentation via Diffusion ModelCode1
Asymmetric Polynomial Loss For Multi-Label ClassificationCode1
Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse DataCode1
Adaptive Mask Sampling and Manifold to Euclidean Subspace Learning with Distance Covariance Representation for Hyperspectral Image ClassificationCode1
SparseFormer: Sparse Visual Recognition via Limited Latent TokensCode1
SMPConv: Self-moving Point Representations for Continuous ConvolutionCode1
Cross-modulated Few-shot Image Generation for Colorectal Tissue ClassificationCode1
VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue DistributionCode1
EGC: Image Generation and Classification via a Diffusion Energy-Based ModelCode1
Astroformer: More Data Might not be all you need for ClassificationCode1
Parents and Children: Distinguishing Multimodal DeepFakes from Natural ImagesCode1
Video Pretraining Advances 3D Deep Learning on Chest CT TasksCode1
Vision Transformers with Mixed-Resolution TokenizationCode1
Rethinking Local Perception in Lightweight Vision TransformerCode1
PMatch: Paired Masked Image Modeling for Dense Geometric MatchingCode1
Fully Hyperbolic Convolutional Neural Networks for Computer VisionCode1
Iteratively Coupled Multiple Instance Learning from Instance to Bag Classifier for Whole Slide Image ClassificationCode1
EVA-CLIP: Improved Training Techniques for CLIP at ScaleCode1
Freestyle Layout-to-Image SynthesisCode1
Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning ParadigmCode1
Prompt Tuning based Adapter for Vision-Language Model AdaptionCode1
Category Query Learning for Human-Object Interaction ClassificationCode1
The effectiveness of MAE pre-pretraining for billion-scale pretrainingCode1
Take 5: Interpretable Image Classification with a Handful of FeaturesCode1
Show:102550
← PrevPage 16 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