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 831840 of 10420 papers

TitleStatusHype
4-bit Shampoo for Memory-Efficient Network TrainingCode1
All you need is a good initCode1
Channel Importance Matters in Few-Shot Image ClassificationCode1
CLCC: Contrastive Learning for Color ConstancyCode1
An Open-source Tool for Hyperspectral Image Augmentation in TensorflowCode1
ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax DiseasesCode1
Automated detection of COVID-19 cases from chest X-ray images using deep neural network and XGBoostCode1
Fair Federated Medical Image Classification Against Quality Shift via Inter-Client Progressive State MatchingCode1
ViViT: A Video Vision TransformerCode1
Deep Roto-Translation Scattering for Object ClassificationCode1
Show:102550
← PrevPage 84 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
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