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 88768900 of 10420 papers

TitleStatusHype
Tencent ML-Images: A Large-Scale Multi-Label Image Database for Visual Representation LearningCode2
Multi-Objective Reinforced Evolution in Mobile Neural Architecture SearchCode0
Adversarial Examples Versus Cloud-based Detectors: A Black-box Empirical Study0
A Hierarchical Grocery Store Image Dataset with Visual and Semantic LabelsCode0
A Comprehensive Survey on Graph Neural NetworksCode1
On Minimum Discrepancy Estimation for Deep Domain AdaptationCode1
Learning Efficient Detector with Semi-supervised Adaptive DistillationCode0
Multi-Label Adversarial Perturbations0
A Full Probabilistic Model for Yes/No Type Crowdsourcing in Multi-Class ClassificationCode0
Sample-Efficient Neural Architecture Search by Learning Action Space for Monte Carlo Tree Search0
LiSHT: Non-Parametric Linearly Scaled Hyperbolic Tangent Activation Function for Neural NetworksCode0
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
Fine-tuning Convolutional Neural Networks for fine art classification0
Monte-Carlo Sampling applied to Multiple Instance Learning for Histological Image Classification0
DART: Domain-Adversarial Residual-Transfer Networks for Unsupervised Cross-Domain Image Classification0
Greedy Layerwise Learning Can Scale to ImageNetCode0
Neural Architecture Search Over a Graph Search Space0
Adversarial Attack and Defense on Graph Data: A SurveyCode0
Studying the Plasticity in Deep Convolutional Neural Networks using Random PruningCode1
Attention Branch Network: Learning of Attention Mechanism for Visual ExplanationCode0
Privacy-Preserving Collaborative Deep Learning with Unreliable Participants0
Guessing Smart: Biased Sampling for Efficient Black-Box Adversarial AttacksCode0
Learning from Web Data: the Benefit of Unsupervised Object Localization0
Show:102550
← PrevPage 356 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