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 12511275 of 10420 papers

TitleStatusHype
Augmenting Convolutional networks with attention-based aggregationCode1
ELSA: Enhanced Local Self-Attention for Vision TransformerCode1
RepMLPNet: Hierarchical Vision MLP with Re-parameterized LocalityCode1
Learned Queries for Efficient Local AttentionCode1
Transformers Can Do Bayesian InferenceCode1
HarmoFL: Harmonizing Local and Global Drifts in Federated Learning on Heterogeneous Medical ImagesCode1
UniMiSS: Universal Medical Self-Supervised Learning via Breaking Dimensionality BarrierCode1
Towards End-to-End Image Compression and Analysis with TransformersCode1
Pixel Distillation: A New Knowledge Distillation Scheme for Low-Resolution Image RecognitionCode1
Learning to Prompt for Continual LearningCode1
RegionCLIP: Region-based Language-Image PretrainingCode1
An Empirical Investigation of the Role of Pre-training in Lifelong LearningCode1
Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise ImagesCode1
Towards General and Efficient Active LearningCode1
AdaViT: Adaptive Tokens for Efficient Vision TransformerCode1
Heuristic Hyperparameter Optimization for Convolutional Neural Networks using Genetic AlgorithmCode1
WOOD: Wasserstein-based Out-of-Distribution DetectionCode1
Simple and Robust Loss Design for Multi-Label Learning with Missing LabelsCode1
Boosting Active Learning via Improving Test PerformanceCode1
The Large Labelled Logo Dataset (L3D): A Multipurpose and Hand-Labelled Continuously Growing DatasetCode1
Visual Transformers with Primal Object Queries for Multi-Label Image ClassificationCode1
Locally Shifted Attention With Early Global IntegrationCode1
Obtaining Calibrated Probabilities with Personalized Ranking ModelsCode1
PE-former: Pose Estimation TransformerCode1
A Contrastive Distillation Approach for Incremental Semantic Segmentation in Aerial ImagesCode1
Show:102550
← PrevPage 51 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