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 58265850 of 10420 papers

TitleStatusHype
Scaling Vision with Sparse Mixture of ExpertsCode1
Verifying Quantized Neural Networks using SMT-Based Model Checking0
PeCLR: Self-Supervised 3D Hand Pose Estimation from monocular RGB via Equivariant Contrastive LearningCode1
Deep neural network loses attention to adversarial images0
Cross-domain Contrastive Learning for Unsupervised Domain AdaptationCode0
CoAtNet: Marrying Convolution and Attention for All Data SizesCode1
CLCC: Contrastive Learning for Color ConstancyCode1
Cervical Cytology Classification Using PCA & GWO Enhanced Deep Features SelectionCode1
Knowledge distillation: A good teacher is patient and consistentCode2
Salient Positions based Attention Network for Image ClassificationCode1
Rethinking Transfer Learning for Medical Image ClassificationCode1
Exploiting auto-encoders and segmentation methods for middle-level explanations of image classification systems0
Explainable AI for medical imaging: Explaining pneumothorax diagnoses with Bayesian Teaching0
To Smooth or Not? When Label Smoothing Meets Noisy LabelsCode1
The Randomness of Input Data Spaces is an A Priori Predictor for Generalization0
Self-Supervised Learning with Data Augmentations Provably Isolates Content from StyleCode1
Scaling Vision Transformers0
SpaceMeshLab: Spatial Context Memoization and Meshgrid Atrous Convolution Consensus for Semantic Segmentation0
Benchmarking Bias Mitigation Algorithms in Representation Learning through Fairness MetricsCode1
MONCAE: Multi-Objective Neuroevolution of Convolutional Autoencoders0
TENGraD: Time-Efficient Natural Gradient Descent with Exact Fisher-Block InversionCode0
Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-grained EnvironmentsCode1
An Intelligent Hybrid Model for Identity Document Classification0
Frustratingly Easy Uncertainty Estimation for Distribution Shift0
ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive BiasCode1
Show:102550
← PrevPage 234 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