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 501525 of 10419 papers

TitleStatusHype
DeepVoxNet2: Yet another CNN frameworkCode1
Defending Against Unforeseen Failure Modes with Latent Adversarial TrainingCode1
3D Human Pose Estimation with Spatial and Temporal TransformersCode1
Counterfactual Explanations for Medical Image Classification and Regression using Diffusion AutoencoderCode1
ACPL: Anti-curriculum Pseudo-labelling for Semi-supervised Medical Image ClassificationCode1
Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy LabelsCode1
Balanced Contrastive Learning for Long-Tailed Visual RecognitionCode1
Balanced-MixUp for Highly Imbalanced Medical Image ClassificationCode1
Balanced Energy Regularization Loss for Out-of-distribution DetectionCode1
Delving into Out-of-Distribution Detection with Medical Vision-Language ModelsCode1
Convolutional Channel-wise Competitive Learning for the Forward-Forward AlgorithmCode1
Contrastive Learning of Medical Visual Representations from Paired Images and TextCode1
Contrastive Learning of Generalized Game RepresentationsCode1
CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image ClassificationCode1
A Simple Baseline for Low-Budget Active LearningCode1
Contrastive Losses Are Natural Criteria for Unsupervised Video SummarizationCode1
Convolutional Sequence to Sequence LearningCode1
Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional UnderstandingCode1
Contrastive Deep SupervisionCode1
Layer-adaptive sparsity for the Magnitude-based PruningCode1
ConTNet: Why not use convolution and transformer at the same time?Code1
Contrastive Learning Improves Model Robustness Under Label NoiseCode1
A Robust Feature Downsampling Module for Remote Sensing Visual TasksCode1
A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data AugmentationCode1
A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network CalibrationCode1
Show:102550
← PrevPage 21 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