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 89769000 of 10420 papers

TitleStatusHype
Unsupervised Visual Feature Learning with Spike-timing-dependent Plasticity: How Far are we from Traditional Feature Learning Approaches?0
A Machine-Synesthetic Approach To DDoS Network Attack Detection0
Generating Adversarial Perturbation with Root Mean Square Gradient0
FishNet: A Versatile Backbone for Image, Region, and Pixel Level PredictionCode0
Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud ClassifiersCode0
Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image SegmentationCode0
Variable Importance Clouds: A Way to Explore Variable Importance for the Set of Good ModelsCode0
Is it Time to Swish? Comparing Deep Learning Activation Functions Across NLP tasksCode0
How Compact?: Assessing Compactness of Representations through Layer-Wise Pruning0
A Comprehensive guide to Bayesian Convolutional Neural Network with Variational InferenceCode0
Guidelines and Benchmarks for Deployment of Deep Learning Models on Smartphones as Real-Time AppsCode0
Deep Neural Network Approximation Theory0
Ensembles of feedforward-designed convolutional neural networks0
Adversarial Examples Versus Cloud-based Detectors: A Black-box Empirical Study0
Multi-Objective Reinforced Evolution in Mobile Neural Architecture SearchCode0
A Hierarchical Grocery Store Image Dataset with Visual and Semantic LabelsCode0
Multi-Label Adversarial Perturbations0
A Full Probabilistic Model for Yes/No Type Crowdsourcing in Multi-Class ClassificationCode0
Learning Efficient Detector with Semi-supervised Adaptive DistillationCode0
LiSHT: Non-Parametric Linearly Scaled Hyperbolic Tangent Activation Function for Neural NetworksCode0
Sample-Efficient Neural Architecture Search by Learning Action Space for Monte Carlo Tree Search0
Morphological Network: How Far Can We Go with Morphological Neurons?0
Training with the Invisibles: Obfuscating Images to Share Safely for Learning Visual Recognition Models0
Deep Residual Learning in the JPEG Transform DomainCode0
Monte-Carlo Sampling applied to Multiple Instance Learning for Histological Image Classification0
Show:102550
← PrevPage 360 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