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 13761400 of 10419 papers

TitleStatusHype
No Routing Needed Between CapsulesCode1
CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped WindowsCode1
Function-Consistent Feature DistillationCode1
Curriculum Temperature for Knowledge DistillationCode1
Bayesian Model-Agnostic Meta-LearningCode1
Bayesian Neural Network Priors RevisitedCode1
GAN-based Priors for Quantifying UncertaintyCode1
Achieving Fairness Through Channel Pruning for Dermatological Disease DiagnosisCode1
Gaussian RAM: Lightweight Image Classification via Stochastic Retina-Inspired Glimpse and Reinforcement LearningCode1
Bayesian Optimization Meets Self-DistillationCode1
General E(2)-Equivariant Steerable CNNsCode1
A Survey of Classical And Quantum Sequence ModelsCode1
Generalized Jensen-Shannon Divergence Loss for Learning with Noisy LabelsCode1
Cross-modal Adversarial ReprogrammingCode1
General Multi-label Image Classification with TransformersCode1
Active Learning for Convolutional Neural Networks: A Core-Set ApproachCode1
Cross-modulated Few-shot Image Generation for Colorectal Tissue ClassificationCode1
Fcaformer: Forward Cross Attention in Hybrid Vision TransformerCode1
Generative Hierarchical Features from Synthesizing ImagesCode1
A Survey: Deep Learning for Hyperspectral Image Classification with Few Labeled SamplesCode1
Cross-Iteration Batch NormalizationCode1
Generic Neural Architecture Search via RegressionCode1
Generic-to-Specific Distillation of Masked AutoencodersCode1
BEV-LGKD: A Unified LiDAR-Guided Knowledge Distillation Framework for BEV 3D Object DetectionCode1
AutoAssist: A Framework to Accelerate Training of Deep Neural NetworksCode1
Show:102550
← PrevPage 56 of 417Next →

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
5DaViT-HTop 1 Accuracy90.2Unverified
6Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2Unverified
7SwinV2-GTop 1 Accuracy90.17Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05Unverified
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90Unverified