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 16411650 of 10420 papers

TitleStatusHype
The Low-Rank Simplicity Bias in Deep NetworksCode1
MSMatch: Semi-Supervised Multispectral Scene Classification with Few LabelsCode1
Consistency-based Active Learning for Object DetectionCode1
Triplet-Watershed for Hyperspectral Image ClassificationCode1
Gradient Projection Memory for Continual LearningCode1
Deep Reinforcement Learning for Band Selection in Hyperspectral Image ClassificationCode1
UPANets: Learning from the Universal Pixel Attention NetworksCode1
TransFG: A Transformer Architecture for Fine-grained RecognitionCode1
Membership Inference Attacks on Machine Learning: A SurveyCode1
Revisiting ResNets: Improved Training and Scaling StrategiesCode1
Show:102550
← PrevPage 165 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