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 451475 of 10419 papers

TitleStatusHype
Attack of the Tails: Yes, You Really Can Backdoor Federated LearningCode1
Attentional Feature FusionCode1
Confidence Regularized Self-TrainingCode1
Conformer: Local Features Coupling Global Representations for Visual RecognitionCode1
Attention based Dual-Branch Complex Feature Fusion Network for Hyperspectral Image ClassificationCode1
Adversarial Example Detection for DNN Models: A Review and Experimental ComparisonCode1
Attention-Based Second-Order Pooling Network for Hyperspectral Image ClassificationCode1
Attention-Challenging Multiple Instance Learning for Whole Slide Image ClassificationCode1
Continual atlas-based segmentation of prostate MRICode1
Adversarial Examples in Deep Learning for Multivariate Time Series RegressionCode1
A Comprehensive Survey on Graph Neural NetworksCode1
Contrastive Learning Improves Model Robustness Under Label NoiseCode1
Learning Hierarchical Image Segmentation For Recognition and By RecognitionCode1
Attribute Descent: Simulating Object-Centric Datasets on the Content Level and BeyondCode1
AugNet: End-to-End Unsupervised Visual Representation Learning with Image AugmentationCode1
CycleMLP: A MLP-like Architecture for Dense PredictionCode1
Augmentation Strategies for Learning with Noisy LabelsCode1
Augmentation-Free Dense Contrastive Knowledge Distillation for Efficient Semantic SegmentationCode1
Concurrent Spatial and Channel Squeeze & Excitation in Fully Convolutional NetworksCode1
Arch-Net: Model Distillation for Architecture Agnostic Model DeploymentCode1
Masking meets Supervision: A Strong Learning AllianceCode1
Augmenting Convolutional networks with attention-based aggregationCode1
DarkneTZ: Towards Model Privacy at the Edge using Trusted Execution EnvironmentsCode1
DARTS: Differentiable Architecture SearchCode1
3D Human Pose Estimation with Spatial and Temporal TransformersCode1
Show:102550
← PrevPage 19 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