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 50015025 of 10420 papers

TitleStatusHype
Visual Transformers with Primal Object Queries for Multi-Label Image ClassificationCode1
Tradeoffs Between Contrastive and Supervised Learning: An Empirical Study0
Boosting Active Learning via Improving Test PerformanceCode1
The Large Labelled Logo Dataset (L3D): A Multipurpose and Hand-Labelled Continuously Growing DatasetCode1
Couplformer:Rethinking Vision Transformer with Coupling Attention MapCode0
Global Attention Mechanism: Retain Information to Enhance Channel-Spatial InteractionsCode0
Obtaining Calibrated Probabilities with Personalized Ranking ModelsCode1
Knowledge Distillation for Object Detection via Rank Mimicking and Prediction-guided Feature Imitation0
PE-former: Pose Estimation TransformerCode1
Amicable Aid: Perturbing Images to Improve Classification Performance0
Locally Shifted Attention With Early Global IntegrationCode1
Guardian of the Ensembles: Introducing Pairwise Adversarially Robust Loss for Resisting Adversarial Attacks in DNN EnsemblesCode0
Pareto Domain AdaptationCode0
Boosting Deep Ensemble Performance with Hierarchical PruningCode0
Few-Shot Image Classification Along Sparse Graphs0
A Contrastive Distillation Approach for Incremental Semantic Segmentation in Aerial ImagesCode1
Dilated convolution with learnable spacingsCode1
Augment & Valuate : A Data Enhancement Pipeline for Data-Centric AI0
Extrapolation Frameworks in Cognitive Psychology Suitable for Study of Image Classification Models0
Manas: Mining Software Repositories to Assist AutoMLCode0
Test-Time Detection of Backdoor Triggers for Poisoned Deep Neural Networks0
ML Attack Models: Adversarial Attacks and Data Poisoning Attacks0
Curriculum Meta-Learning for Few-shot ClassificationCode0
Two Wrongs Don't Make a Right: Combating Confirmation Bias in Learning with Label Noise0
Finding Deviated Behaviors of the Compressed DNN Models for Image ClassificationsCode0
Show:102550
← PrevPage 201 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