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 151200 of 10419 papers

TitleStatusHype
Knowledge distillation: A good teacher is patient and consistentCode2
Fixing the train-test resolution discrepancyCode2
FasterViT: Fast Vision Transformers with Hierarchical AttentionCode2
Fixing the train-test resolution discrepancy: FixEfficientNetCode2
EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space DualityCode2
EMR-Merging: Tuning-Free High-Performance Model MergingCode2
FixMatch: Simplifying Semi-Supervised Learning with Consistency and ConfidenceCode2
Efficient Multi-Scale Attention Module with Cross-Spatial LearningCode2
UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene ImageryCode2
Adapter is All You Need for Tuning Visual TasksCode2
MobileOne: An Improved One millisecond Mobile BackboneCode2
EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision ApplicationsCode2
Effective Data Augmentation With Diffusion ModelsCode2
ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural NetworksCode2
An Overview of Deep Semi-Supervised LearningCode2
MogaNet: Multi-order Gated Aggregation NetworkCode2
AdaFisher: Adaptive Second Order Optimization via Fisher InformationCode2
ParC-Net: Position Aware Circular Convolution with Merits from ConvNets and TransformerCode2
FixMatch: Simplifying Semi-Supervised Learning with Consistency and ConfidenceCode2
DEYO: DETR with YOLO for End-to-End Object DetectionCode2
ERS: a novel comprehensive endoscopy image dataset for machine learning, compliant with the MST 3.0 specificationCode2
DGR-MIL: Exploring Diverse Global Representation in Multiple Instance Learning for Whole Slide Image ClassificationCode2
Fast Vision Transformers with HiLo AttentionCode2
DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTsCode2
Deep PCB To COCO ConvertorCode2
Accelerating Transformers with Spectrum-Preserving Token MergingCode2
A Self-Supervised Descriptor for Image Copy DetectionCode2
Frontiers in Intelligent ColonoscopyCode2
2DMamba: Efficient State Space Model for Image Representation with Applications on Giga-Pixel Whole Slide Image ClassificationCode2
A Simple Episodic Linear Probe Improves Visual Recognition in the WildCode2
A Simple Framework for Contrastive Learning of Visual RepresentationsCode2
Generalized Parametric Contrastive LearningCode2
Global Context Vision TransformersCode2
GPipe: Efficient Training of Giant Neural Networks using Pipeline ParallelismCode2
GrootVL: Tree Topology is All You Need in State Space ModelCode2
GroupMamba: Efficient Group-Based Visual State Space ModelCode2
Decoupled Knowledge DistillationCode2
HorNet: Efficient High-Order Spatial Interactions with Recursive Gated ConvolutionsCode2
DaViT: Dual Attention Vision TransformersCode2
Class-Incremental Learning: A SurveyCode2
Dilated Neighborhood Attention TransformerCode2
DAMamba: Vision State Space Model with Dynamic Adaptive ScanCode2
DataDream: Few-shot Guided Dataset GenerationCode2
LayoutLM: Pre-training of Text and Layout for Document Image UnderstandingCode2
Current Trends in Deep Learning for Earth Observation: An Open-source Benchmark Arena for Image ClassificationCode2
Learning Transferable Visual Models From Natural Language SupervisionCode2
LibFewShot: A Comprehensive Library for Few-shot LearningCode2
CrossFormer++: A Versatile Vision Transformer Hinging on Cross-scale AttentionCode2
3D-RCNet: Learning from Transformer to Build a 3D Relational ConvNet for Hyperspectral Image ClassificationCode2
CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View CompletionCode2
Show:102550
← PrevPage 4 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