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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 7851–7875 of 10420 papers

TitleStatusHype
Deep Curriculum Learning for PolSAR Image Classification—0
Recurrent Neural Networks to Correct Satellite Image Classification Maps—0
Improving Object Detection with Selective Self-supervised Self-training—0
Deep Co-Space: Sample Mining Across Feature Transformation for Semi-Supervised Learning—0
Improving Normalization with the James-Stein Estimator—0
Auto-view contrastive learning for few-shot image recognition—0
Improving Multi-fidelity Optimization with a Recurring Learning Rate for Hyperparameter Tuning—0
Improving Model Performance and Removing the Class Imbalance Problem Using Augmentation—0
Improving Model Accuracy for Imbalanced Image Classification Tasks by Adding a Final Batch Normalization Layer: An Empirical Study—0
ReDistill: Residual Encoded Distillation for Peak Memory Reduction—0
RedSync : Reducing Synchronization Traffic for Distributed Deep Learning—0
Reduced Jeffries-Matusita distance: A Novel Loss Function to Improve Generalization Performance of Deep Classification Models—0
Improving Medical Image Classification with Label Noise Using Dual-uncertainty Estimation—0
Deep Convolutional Spiking Neural Networks for Image Classification—0
Auto-tuning TensorFlow Threading Model for CPU Backend—0
Reducing Implicit Bias in Latent Domain Learning—0
Adaptive Cross-Attention-Driven Spatial-Spectral Graph Convolutional Network for Hyperspectral Image Classification—0
Reducing Textural Bias Improves Robustness of Deep Segmentation Models—0
Improving Machine Reading Comprehension via Adversarial Training—0
FedChain: Chained Algorithms for Near-Optimal Communication Cost in Federated Learning—0
Improving Layer-wise Adaptive Rate Methods using Trust Ratio Clipping—0
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning—0
Redundant Information Neural Estimation—0
Improving Label Error Detection and Elimination with Uncertainty Quantification—0
Deep Convolutional Neural Networks as Generic Feature Extractors—0
Show:102550
← PrevPage 315 of 417Next →
All datasetsImageNetCIFAR-10CIFAR-100STL-10ObjectNetMNISTSVHNiNaturalist 2018ImageNet ReaLFlowers-102Clothing1Mmini WebVision 1.0

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CoCa (finetuned)Top 1 Accuracy91—Unverified
2Model soups (BASIC-L)Top 1 Accuracy90.98—Unverified
3Model soups (ViT-G/14)Top 1 Accuracy90.94—Unverified
4DaViT-GTop 1 Accuracy90.4—Unverified
5DaViT-HTop 1 Accuracy90.2—Unverified
6Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2—Unverified
7SwinV2-GTop 1 Accuracy90.17—Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1—Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05—Unverified
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90—Unverified