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 20262050 of 10420 papers

TitleStatusHype
SimLoss: Class Similarities in Cross EntropyCode1
Combating noisy labels by agreement: A joint training method with co-regularizationCode1
AIDeveloper: deep learning image classification in life science and beyondCode1
Feature Extraction for Hyperspectral Imagery: The Evolution from Shallow to Deep (Overview and Toolbox)Code1
Denoised Smoothing: A Provable Defense for Pretrained ClassifiersCode1
Curriculum By SmoothingCode1
Out-of-Distribution Generalization via Risk Extrapolation (REx)Code1
RNNPool: Efficient Non-linear Pooling for RAM Constrained InferenceCode1
FMix: Enhancing Mixed Sample Data AugmentationCode1
Towards Interpretable Semantic Segmentation via Gradient-weighted Class Activation MappingCode1
A Comprehensive Approach to Unsupervised Embedding Learning based on AND AlgorithmCode1
On Feature Normalization and Data AugmentationCode1
I Am Going MAD: Maximum Discrepancy Competition for Comparing Classifiers AdaptivelyCode1
Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural NetworksCode1
Scheduled Restart Momentum for Accelerated Stochastic Gradient DescentCode1
Stochasticity in Neural ODEs: An Empirical StudyCode1
A Toolkit for Generating Code Knowledge GraphsCode1
Towards Robust and Reproducible Active Learning Using Neural NetworksCode1
KaoKore: A Pre-modern Japanese Art Facial Expression DatasetCode1
Algorithm-hardware Co-design for Deformable ConvolutionCode1
DivideMix: Learning with Noisy Labels as Semi-supervised LearningCode1
Multi-Scale Representation Learning for Spatial Feature Distributions using Grid CellsCode1
Breast Cancer Histopathology Image Classification and Localization using Multiple Instance LearningCode1
Superpixel Image Classification with Graph Attention NetworksCode1
Scalable and Practical Natural Gradient for Large-Scale Deep LearningCode1
Show:102550
← PrevPage 82 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
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