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 83768400 of 10420 papers

TitleStatusHype
Densely Connected Search Space for More Flexible Neural Architecture SearchCode0
Database Meets Deep Learning: Challenges and Opportunities0
Deep-Learning-Based Aerial Image Classification for Emergency Response Applications Using Unmanned Aerial VehiclesCode1
Understanding More about Human and Machine Attention in Deep Neural Networks0
Unsupervised Learning of Object Keypoints for Perception and ControlCode1
The Functional Neural ProcessCode0
ViP: Virtual Pooling for Accelerating CNN-based Image Classification and Object DetectionCode0
XNAS: Neural Architecture Search with Expert AdviceCode1
Automatic estimation of heading date of paddy rice using deep learning0
A simple and effective postprocessing method for image classification0
Cloud-based Image Classification Service Is Not Robust To Simple Transformations: A Forgotten Battlefield0
Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive ProcessesCode1
Active Generative Adversarial Network for Image Classification0
PolSAR Image Classification based on Polarimetric Scattering Coding and Sparse Support Matrix Machine0
Three-Dimensional Fourier Scattering Transform and Classification of Hyperspectral ImagesCode0
Mixture separability loss in a deep convolutional network for image classification0
Equivariant neural networks and equivarificationCode0
SELFIE: Refurbishing Unclean Samples for Robust Deep LearningCode0
Fixing the train-test resolution discrepancyCode2
Adversarial Robustness Assessment: Why both L_0 and L_ Attacks Are NecessaryCode0
A Partially Reversible U-Net for Memory-Efficient Volumetric Image SegmentationCode1
A Signal Propagation Perspective for Pruning Neural Networks at InitializationCode0
Factorized Higher-Order CNNs with an Application to Spatio-Temporal Emotion Estimation0
Deep Learning Development Environment in Virtual RealityCode0
Near-Optimal Glimpse Sequences for Improved Hard Attention Neural Network Training0
Show:102550
← PrevPage 336 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
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90Unverified