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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 2976–3000 of 10420 papers

TitleStatusHype
DC3DCD: unsupervised learning for multiclass 3D point cloud change detectionCode1
Semantic Embedded Deep Neural Network: A Generic Approach to Boost Multi-Label Image Classification Performance—0
Investigating the Corruption Robustness of Image Classifiers with Random Lp-norm CorruptionsCode0
LABO: Towards Learning Optimal Label Regularization via Bi-level Optimization—0
Understanding Gaussian Attention Bias of Vision Transformers Using Effective Receptive FieldsCode0
Creative Discovery using QD SearchCode0
Pick your Poison: Undetectability versus Robustness in Data Poisoning Attacks—0
Boldness-Recalibration for Binary Event Predictions—0
Reduction of Class Activation Uncertainty with Background InformationCode1
Semantic Segmentation using Vision Transformers: A survey—0
Human Attention-Guided Explainable Artificial Intelligence for Computer Vision Models—0
Breast Cancer Diagnosis Using Machine Learning Techniques—0
LatentAugment: Dynamically Optimized Latent Probabilities of Data AugmentationCode0
Forward-Forward Contrastive Learning—0
Image Captioners Sometimes Tell More Than Images They See—0
Unsupervised Mutual Transformer Learning for Multi-Gigapixel Whole Slide Image Classification—0
mAedesID: Android Application for Aedes Mosquito Species Identification using Convolutional Neural Network—0
Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth LabelsCode1
On the Impact of Data Quality on Image Classification Fairness—0
CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual RepresentationsCode1
FCA: Taming Long-tailed Federated Medical Image Classification by Classifier AnchoringCode0
TPMIL: Trainable Prototype Enhanced Multiple Instance Learning for Whole Slide Image ClassificationCode0
Detecting Novelties with Empty Classes—0
Instruction-ViT: Multi-Modal Prompts for Instruction Learning in ViT—0
POUF: Prompt-oriented unsupervised fine-tuning for large pre-trained modelsCode1
Show:102550
← PrevPage 120 of 417Next →
All datasetsImageNetCIFAR-10CIFAR-100STL-10ObjectNetMNISTSVHNiNaturalist 2018ImageNet ReaLFlowers-102Clothing1Mmini WebVision 1.0

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CoCa (finetuned)Top 1 Accuracy91—Unverified
2Model soups (BASIC-L)Top 1 Accuracy90.98—Unverified
3Model soups (ViT-G/14)Top 1 Accuracy90.94—Unverified
4DaViT-GTop 1 Accuracy90.4—Unverified
5Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2—Unverified
6DaViT-HTop 1 Accuracy90.2—Unverified
7SwinV2-GTop 1 Accuracy90.17—Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1—Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05—Unverified
10RevCol-HTop 1 Accuracy90—Unverified