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 98269850 of 10420 papers

TitleStatusHype
Unsupervised part learning for visual recognition0
Improving Pairwise Ranking for Multi-label Image ClassificationCode0
Cutting the Error by Half: Investigation of Very Deep CNN and Advanced Training Strategies for Document Image ClassificationCode0
Fine-graind Image Classification via Combining Vision and Language0
Using convolutional networks and satellite imagery to identify patterns in urban environments at a large scaleCode0
Supervised Infinite Feature SelectionCode0
Enhancing Robustness of Machine Learning Systems via Data Transformations0
Encoder Based Lifelong Learning0
Object-Part Attention Model for Fine-grained Image ClassificationCode0
On Generalization and Regularization in Deep Learning0
Classification of Diabetic Retinopathy Images Using Multi-Class Multiple-Instance Learning Based on Color Correlogram Features0
The Relative Performance of Ensemble Methods with Deep Convolutional Neural Networks for Image ClassificationCode0
Truncating Wide Networks using Binary Tree ArchitecturesCode0
A Genetic Programming Approach to Designing Convolutional Neural Network ArchitecturesCode0
Tube Convolutional Neural Network (T-CNN) for Action Detection in VideosCode0
Bundle Optimization for Multi-aspect Embedding0
Active Convolution: Learning the Shape of Convolution for Image ClassificationCode0
Scaling the Scattering Transform: Deep Hybrid NetworksCode0
Deceiving Google's Cloud Video Intelligence API Built for Summarizing Videos0
Knowledge Transfer for Melanoma Screening with Deep LearningCode0
Cross-View Image Matching for Geo-localization in Urban EnvironmentsCode0
Joint Intermodal and Intramodal Label Transfers for Extremely Rare or Unseen Classes0
Knowledge distillation using unlabeled mismatched images0
Second-order Convolutional Neural Networks0
Curriculum DropoutCode0
Show:102550
← PrevPage 394 of 417Next →

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