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 16011625 of 10419 papers

TitleStatusHype
DecAug: Out-of-Distribution Generalization via Decomposed Feature Representation and Semantic AugmentationCode1
MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without TricksCode1
Decoupled Dynamic Filter NetworksCode1
DeBiFormer: Vision Transformer with Deformable Agent Bi-level Routing AttentionCode1
A General Regret Bound of Preconditioned Gradient Method for DNN TrainingCode1
Deblurring Masked Autoencoder is Better Recipe for Ultrasound Image RecognitionCode1
Merging Feed-Forward Sublayers for Compressed TransformersCode1
Meta-Adapter: An Online Few-shot Learner for Vision-Language ModelCode1
Meta-Album: Multi-domain Meta-Dataset for Few-Shot Image ClassificationCode1
MetaAudio: A Few-Shot Audio Classification BenchmarkCode1
DCN-T: Dual Context Network with Transformer for Hyperspectral Image ClassificationCode1
DC3DCD: unsupervised learning for multiclass 3D point cloud change detectionCode1
MetaLA: Unified Optimal Linear Approximation to Softmax Attention MapCode1
Meta-Learning with Fewer Tasks through Task InterpolationCode1
DCT-CryptoNets: Scaling Private Inference in the Frequency DomainCode1
DEAL: Deep Evidential Active Learning for Image ClassificationCode1
TransCenter: Transformers with Dense Representations for Multiple-Object TrackingCode1
Fcaformer: Forward Cross Attention in Hybrid Vision TransformerCode1
Decoupled Weight Decay RegularizationCode1
Mind's Eye: Image Recognition by EEG via Multimodal Similarity-Keeping Contrastive LearningCode1
Data-Efficient Deep Learning Method for Image Classification Using Data Augmentation, Focal Cosine Loss, and EnsembleCode1
Data Feedback Loops: Model-driven Amplification of Dataset BiasesCode1
Mitigating Embedding and Class Assignment Mismatch in Unsupervised Image ClassificationCode1
Hybrid Supervision Learning for Pathology Whole Slide Image ClassificationCode1
Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)Code1
Show:102550
← PrevPage 65 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