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 95769600 of 10420 papers

TitleStatusHype
Dynamic Routing Between CapsulesCode1
InterpNET: Neural Introspection for Interpretable Deep LearningCode0
Deep Neural Networks0
mixup: Beyond Empirical Risk MinimizationCode1
Incomplete Dot Products for Dynamic Computation Scaling in Neural Network Inference0
Classification Driven Dynamic Image Enhancement0
Deep Self-taught Learning for Remote Sensing Image Classification0
Enhancing the Performance of Convolutional Neural Networks on Quality Degraded Datasets0
VisDA: The Visual Domain Adaptation ChallengeCode1
Dropout Sampling for Robust Object Detection in Open-Set Conditions0
Do Convolutional Neural Networks Learn Class Hierarchy?0
Learning to Learn Image Classifiers with Visual Analogy0
Entanglement Entropy of Target Functions for Image Classification and Convolutional Neural Network0
Searching for Activation FunctionsCode0
Pushing the envelope in deep visual recognition for mobile platforms0
Manifold regularization based on Nyström type subsampling0
Arguing Machines: Human Supervision of Black Box AI Systems That Make Life-Critical DecisionsCode0
Convolutional Neural Networks for Histopathology Image Classification: Training vs. Using Pre-Trained Networks0
Learning to Generalize: Meta-Learning for Domain GeneralizationCode1
Energy-efficient Amortized Inference with Cascaded Deep Classifiers0
Application of Deep Learning in Neuroradiology: Automated Detection of Basal Ganglia Hemorrhage using 2D-Convolutional Neural Networks0
Does Normalization Methods Play a Role for Hyperspectral Image Classification?0
Deep Convolutional Neural Networks as Generic Feature Extractors0
Energy-Based Spherical Sparse Coding0
A concatenating framework of shortcut convolutional neural networks0
Show:102550
← PrevPage 384 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