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 16811690 of 10420 papers

TitleStatusHype
OntoZSL: Ontology-enhanced Zero-shot LearningCode1
Momentum Residual Neural NetworksCode1
Cross-modal Adversarial ReprogrammingCode1
Bayesian Neural Network Priors RevisitedCode1
Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-TuningCode1
High-Performance Large-Scale Image Recognition Without NormalizationCode1
Training Vision Transformers for Image RetrievalCode1
Clusterability as an Alternative to Anchor Points When Learning with Noisy LabelsCode1
BRECQ: Pushing the Limit of Post-Training Quantization by Block ReconstructionCode1
Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural networkCode1
Show:102550
← PrevPage 169 of 1042Next →

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
5DaViT-HTop 1 Accuracy90.2Unverified
6Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2Unverified
7SwinV2-GTop 1 Accuracy90.17Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05Unverified
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90Unverified