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 25262550 of 10420 papers

TitleStatusHype
Instance-based Label Smoothing For Better Calibrated Classification NetworksCode0
Information Competing Process for Learning Diversified RepresentationsCode0
Inference via Sparse Coding in a Hierarchical Vision ModelCode0
Influence of Image Classification Accuracy on Saliency Map EstimationCode0
An Intelligent Remote Sensing Image Quality Inspection SystemCode0
Intra-class Patch Swap for Self-DistillationCode0
Kannada-MNIST: A new handwritten digits dataset for the Kannada languageCode0
Learnable Adaptive Cosine Estimator (LACE) for Image ClassificationCode0
Understanding Intrinsic Robustness Using Label UncertaintyCode0
AntidoteRT: Run-time Detection and Correction of Poison Attacks on Neural NetworksCode0
Increasing-Margin Adversarial (IMA) Training to Improve Adversarial Robustness of Neural NetworksCode0
Classification Metrics for Image Explanations: Towards Building Reliable XAI-EvaluationsCode0
Adversarial Augmentation for Enhancing Classification of Mammography ImagesCode0
A Comprehensive Study of Image Classification Model Sensitivity to Foregrounds, Backgrounds, and Visual AttributesCode0
Inception-inspired LSTM for Next-frame Video PredictionCode0
Classification Beats Regression: Counting of Cells from Greyscale Microscopic Images based on Annotation-free Training SamplesCode0
Improving Transferability of Adversarial Examples with Input DiversityCode0
Improving the repeatability of deep learning models with Monte Carlo dropoutCode0
Improving the Gating Mechanism of Recurrent Neural NetworksCode0
Improving the trustworthiness of image classification models by utilizing bounding-box annotationsCode0
Improvising the Learning of Neural Networks on Hyperspherical ManifoldCode0
Revisiting 16-bit Neural Network Training: A Practical Approach for Resource-Limited LearningCode0
A Consensual Collaborative Learning Method for Remote Sensing Image Classification Under Noisy Multi-LabelsCode0
Improving singing voice separation with the Wave-U-Net using Minimum Hyperspherical EnergyCode0
Improving robustness to corruptions with multiplicative weight perturbationsCode0
Show:102550
← PrevPage 102 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