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 36813690 of 10420 papers

TitleStatusHype
Adaptive aggregation of Monte Carlo augmented decomposed filters for efficient group-equivariant convolutional neural networkCode0
Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGradCode0
Image classification in frequency domain with 2SReLU: a second harmonics superposition activation functionCode0
A Benchmark for Interpretability Methods in Deep Neural NetworksCode0
Evaluating Generalization Ability of Convolutional Neural Networks and Capsule Networks for Image Classification via Top-2 ClassificationCode0
Decision Forests, Convolutional Networks and the Models in-BetweenCode0
DecisioNet: A Binary-Tree Structured Neural NetworkCode0
Automated Seed Quality Testing System using GAN & Active LearningCode0
Evaluating ResNeXt Model Architecture for Image ClassificationCode0
Automated Search for Configurations of Deep Neural Network ArchitecturesCode0
Show:102550
← PrevPage 369 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