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 21012110 of 10420 papers

TitleStatusHype
Hidden Trigger Backdoor AttacksCode1
Pixel-Wise PolSAR Image Classification via a Novel Complex-Valued Deep Fully Convolutional NetworkCode1
Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAMLCode1
3D U^2-Net: A 3D Universal U-Net for Multi-Domain Medical Image SegmentationCode1
Confidence Regularized Self-TrainingCode1
Learning Filter Basis for Convolutional Neural Network CompressionCode1
Dynamic Graph Message Passing NetworksCode1
Demystifying Learning Rate Policies for High Accuracy Training of Deep Neural NetworksCode1
On the Variance of the Adaptive Learning Rate and BeyondCode1
Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised LearningCode1
Show:102550
← PrevPage 211 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
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90Unverified