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 67016725 of 10420 papers

TitleStatusHype
StackMix: A complementary Mix algorithm0
Contrastive Representation Learning for Whole Brain Cytoarchitectonic Mapping in Histological Human Brain Sections0
torchdistill: A Modular, Configuration-Driven Framework for Knowledge Distillation0
No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification ProblemsCode1
Applying Convolutional Neural Networks to Data on Unstructured Meshes with Space-Filling CurvesCode0
A New Periocular Dataset Collected by Mobile Devices in Unconstrained Scenarios0
Benchmarking Inference Performance of Deep Learning Models on Analog Devices0
Mixture-based Feature Space Learning for Few-shot Image ClassificationCode1
Towards Imperceptible Universal Attacks on Texture Recognition0
Adam^+: A Stochastic Method with Adaptive Variance Reduction0
KeepAugment: A Simple Information-Preserving Data Augmentation ApproachCode1
Exploring Alternatives to Softmax FunctionCode0
Cancer image classification based on DenseNet model0
Uncovering the Bias in Facial Expressions0
Better Aggregation in Test-Time Augmentation0
Unsupervised Difficulty Estimation with Action Scores0
Dense open-set recognition with synthetic outliers generated by Real NVPCode0
Learning Class Unique Features in Fine-Grained Visual Classification0
Head Network Distillation: Splitting Distilled Deep Neural Networks for Resource-Constrained Edge Computing SystemsCode1
An Effective Anti-Aliasing Approach for Residual Networks0
Large Scale Neural Architecture Search with Polyharmonic Splines0
Error-Bounded Correction of Noisy LabelsCode1
DeepRepair: Style-Guided Repairing for DNNs in the Real-world Operational Environment0
Geography-Aware Self-Supervised LearningCode1
On Focal Loss for Class-Posterior Probability Estimation: A Theoretical Perspective0
Show:102550
← PrevPage 269 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