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 39813990 of 10420 papers

TitleStatusHype
BinImg2Vec: Augmenting Malware Binary Image Classification with Data2Vec0
Instance-Dependent Noisy Label Learning via Graphical ModellingCode1
Mayfly optimization with deep learning enabled retinal fundus image classification model0
Ontology of Visual Objects0
Fast Fourier Convolution Based Remote Sensor Image Object Detection for Earth Observation0
Combating Noisy Labels in Long-Tailed Image Classification0
ProCo: Prototype-aware Contrastive Learning for Long-tailed Medical Image ClassificationCode0
Incremental Online Learning Algorithms Comparison for Gesture and Visual Smart Sensors0
Learning with Differentiable Algorithms0
To Store or Not? Online Data Selection for Federated Learning with Limited Storage0
Show:102550
← PrevPage 399 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
10RevCol-HTop 1 Accuracy90Unverified