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 101150 of 10419 papers

TitleStatusHype
K-LITE: Learning Transferable Visual Models with External KnowledgeCode2
HorNet: Efficient High-Order Spatial Interactions with Recursive Gated ConvolutionsCode2
HAIR: Hypernetworks-based All-in-One Image RestorationCode2
HiFuse: Hierarchical Multi-Scale Feature Fusion Network for Medical Image ClassificationCode2
Inception TransformerCode2
LoRA-Pro: Are Low-Rank Adapters Properly Optimized?Code2
Global Context Vision TransformersCode2
GIT: A Generative Image-to-text Transformer for Vision and LanguageCode2
GPipe: Efficient Training of Giant Neural Networks using Pipeline ParallelismCode2
MobileOne: An Improved One millisecond Mobile BackboneCode2
GeoVision Labeler: Zero-Shot Geospatial Classification with Vision and Language ModelsCode2
HGRN2: Gated Linear RNNs with State ExpansionCode2
GreedyViG: Dynamic Axial Graph Construction for Efficient Vision GNNsCode2
Adapter is All You Need for Tuning Visual TasksCode2
GalLoP: Learning Global and Local Prompts for Vision-Language ModelsCode2
Generalized Parametric Contrastive LearningCode2
FSFM: A Generalizable Face Security Foundation Model via Self-Supervised Facial Representation LearningCode2
Frontiers in Intelligent ColonoscopyCode2
Generative Pretraining from PixelsCode2
A Simple Framework for Contrastive Learning of Visual RepresentationsCode2
LambdaNetworks: Modeling Long-Range Interactions Without AttentionCode2
ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural NetworksCode2
A Simple Episodic Linear Probe Improves Visual Recognition in the WildCode2
Learn From Zoom: Decoupled Supervised Contrastive Learning For WCE Image ClassificationCode2
SCAN: Learning to Classify Images without LabelsCode2
Learning Transferable Visual Models From Natural Language SupervisionCode2
GrootVL: Tree Topology is All You Need in State Space ModelCode2
FixMatch: Simplifying Semi-Supervised Learning with Consistency and ConfidenceCode2
Fixing the train-test resolution discrepancy: FixEfficientNetCode2
FixMatch: Simplifying Semi-Supervised Learning with Consistency and ConfidenceCode2
AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed GradientsCode2
3D-RCNet: Learning from Transformer to Build a 3D Relational ConvNet for Hyperspectral Image ClassificationCode2
Fixing the train-test resolution discrepancyCode2
FasterViT: Fast Vision Transformers with Hierarchical AttentionCode2
Fast Vision Transformers with HiLo AttentionCode2
An Overview of Deep Semi-Supervised LearningCode2
AdaFisher: Adaptive Second Order Optimization via Fisher InformationCode2
ERS: a novel comprehensive endoscopy image dataset for machine learning, compliant with the MST 3.0 specificationCode2
Focal Modulation NetworksCode2
GroupMamba: Efficient Group-Based Visual State Space ModelCode2
Efficient Multi-Scale Attention Module with Cross-Spatial LearningCode2
MogaNet: Multi-order Gated Aggregation NetworkCode2
EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space DualityCode2
2DMamba: Efficient State Space Model for Image Representation with Applications on Giga-Pixel Whole Slide Image ClassificationCode2
UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene ImageryCode2
Effective Data Augmentation With Diffusion ModelsCode2
EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision ApplicationsCode2
Dilated Neighborhood Attention TransformerCode2
Aligning Domain-specific Distribution and Classifier for Cross-domain Classification from Multiple SourcesCode2
DGR-MIL: Exploring Diverse Global Representation in Multiple Instance Learning for Whole Slide Image ClassificationCode2
Show:102550
← PrevPage 3 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