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 451500 of 10419 papers

TitleStatusHype
Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional UnderstandingCode1
Continual atlas-based segmentation of prostate MRICode1
Attention-Challenging Multiple Instance Learning for Whole Slide Image ClassificationCode1
Attention-Gated Brain Propagation: How the brain can implement reward-based error backpropagationCode1
Attribute Descent: Simulating Object-Centric Datasets on the Content Level and BeyondCode1
Adversarial Example Detection for DNN Models: A Review and Experimental ComparisonCode1
Attentive WaveBlock: Complementarity-enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-identification and BeyondCode1
Attentive Weights Generation for Few Shot Learning via Information MaximizationCode1
Augmentation-Free Dense Contrastive Knowledge Distillation for Efficient Semantic SegmentationCode1
Adversarial Examples in Deep Learning for Multivariate Time Series RegressionCode1
Continual Hippocampus Segmentation with TransformersCode1
A Robust Feature Downsampling Module for Remote Sensing Visual TasksCode1
A Simple Baseline for Low-Budget Active LearningCode1
Augmented Neural Fine-Tuning for Efficient Backdoor PurificationCode1
Augmenting Convolutional networks with attention-based aggregationCode1
Augmented Neural ODEsCode1
Masking meets Supervision: A Strong Learning AllianceCode1
Data Augmentation with norm-VAE for Unsupervised Domain AdaptationCode1
AugMix: A Simple Data Processing Method to Improve Robustness and UncertaintyCode1
Adversarially-Trained Deep Nets Transfer Better: Illustration on Image ClassificationCode1
Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse DataCode1
AutoDiCE: Fully Automated Distributed CNN Inference at the EdgeCode1
Data Feedback Loops: Model-driven Amplification of Dataset BiasesCode1
DataMUX: Data Multiplexing for Neural NetworksCode1
Contrastive Deep SupervisionCode1
Content-aware Token Sharing for Efficient Semantic Segmentation with Vision TransformersCode1
Contextual Convolutional Neural NetworksCode1
AutoDC: Automated data-centric processingCode1
Can We Talk Models Into Seeing the World Differently?Code1
3D Human Pose Estimation with Spatial and Temporal TransformersCode1
A Contrastive Distillation Approach for Incremental Semantic Segmentation in Aerial ImagesCode1
DeBiFormer: Vision Transformer with Deformable Agent Bi-level Routing AttentionCode1
AutoLRS: Automatic Learning-Rate Schedule by Bayesian Optimization on the FlyCode1
Auto Learning AttentionCode1
Automated detection of COVID-19 cases from chest X-ray images using deep neural network and XGBoostCode1
Automated Learning Rate Scheduler for Large-batch TrainingCode1
Automatically designing CNN architectures using genetic algorithm for image classificationCode1
Decoupled Weight Decay RegularizationCode1
Deep AutoAugmentCode1
Container: Context Aggregation NetworkCode1
Automatic Recognition of Abdominal Organs in Ultrasound Images based on Deep Neural Networks and K-Nearest-Neighbor ClassificationCode1
Deep convolutional tensor networkCode1
DeepEMD: Differentiable Earth Mover's Distance for Few-Shot LearningCode1
Deep Factorized Metric LearningCode1
Spatial and Spatial-Spectral Morphological Mamba for Hyperspectral Image ClassificationCode1
AutoMix: Unveiling the Power of Mixup for Stronger ClassifiersCode1
Contextual Diversity for Active LearningCode1
A Fast 3D CNN for Hyperspectral Image ClassificationCode1
AutoSpeech: Neural Architecture Search for Speaker RecognitionCode1
Confidence Regularized Self-TrainingCode1
Show:102550
← PrevPage 10 of 209Next →

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
5Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2Unverified
6DaViT-HTop 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