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 29212930 of 10420 papers

TitleStatusHype
DenseNet Models for Tiny ImageNet ClassificationCode0
Between-class Learning for Image ClassificationCode0
Exploring Adversarial Robustness of Vision Transformers in the Spectral PerspectiveCode0
Detection of healthy and diseased crops in drone captured images using Deep LearningCode0
Biased Importance Sampling for Deep Neural Network TrainingCode0
In-Place Activated BatchNorm for Memory-Optimized Training of DNNsCode0
DenseNet for Breast Tumor Classification in Mammographic ImagesCode0
DenseNet approach to segmentation and classification of dermatoscopic skin lesions imagesCode0
Better Teacher Better Student: Dynamic Prior Knowledge for Knowledge DistillationCode0
Better Self-training for Image Classification through Self-supervisionCode0
Show:102550
← PrevPage 293 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