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 10011025 of 10419 papers

TitleStatusHype
Container: Context Aggregation NetworkCode1
Improved Baselines with Momentum Contrastive LearningCode1
A Robust Feature Downsampling Module for Remote Sensing Visual TasksCode1
MViTv2: Improved Multiscale Vision Transformers for Classification and DetectionCode1
Improved Online Conformal Prediction via Strongly Adaptive Online LearningCode1
Improved Regularization and Robustness for Fine-tuning in Neural NetworksCode1
A Fast Knowledge Distillation Framework for Visual RecognitionCode1
Confidence-aware multi-modality learning for eye disease screeningCode1
Counterfactual Explanations for Medical Image Classification and Regression using Diffusion AutoencoderCode1
Improving accuracy and speeding up Document Image Classification through parallel systemsCode1
ACPL: Anti-curriculum Pseudo-labelling for Semi-supervised Medical Image ClassificationCode1
Soft-Label Dataset Distillation and Text Dataset DistillationCode1
Improving GAN Training via Feature Space ShrinkageCode1
Improving Generalization in Federated Learning by Seeking Flat MinimaCode1
A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies OthersCode1
Anytime Dense Prediction with Confidence AdaptivityCode1
Improving robustness against common corruptions by covariate shift adaptationCode1
Improving Self-Organizing Maps with Unsupervised Feature ExtractionCode1
A Second-Order Approach to Learning with Instance-Dependent Label NoiseCode1
AwesomeMeta+: A Mixed-Prototyping Meta-Learning System Supporting AI Application Design AnywhereCode1
Improving Visual Prompt Tuning for Self-supervised Vision TransformersCode1
Confidence Regularized Self-TrainingCode1
Content-aware Token Sharing for Efficient Semantic Segmentation with Vision TransformersCode1
Learning Hierarchical Image Segmentation For Recognition and By RecognitionCode1
Concept Learners for Few-Shot LearningCode1
Show:102550
← PrevPage 41 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