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 19512000 of 10419 papers

TitleStatusHype
Combining Metric Learning and Attention Heads For Accurate and Efficient Multilabel Image ClassificationCode1
Are Natural Domain Foundation Models Useful for Medical Image Classification?Code1
GeoWINE: Geolocation based Wiki, Image,News and Event RetrievalCode1
Hyperspectral Image Classification with Attention Aided CNNsCode1
GhostNet: More Features from Cheap OperationsCode1
Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image ClassificationCode1
Confidence Regularized Self-TrainingCode1
I Am Going MAD: Maximum Discrepancy Competition for Comparing Classifiers AdaptivelyCode1
GLiT: Neural Architecture Search for Global and Local Image TransformerCode1
Global Filter Networks for Image ClassificationCode1
Hyperspectral Image Classification-Traditional to Deep Models: A Survey for Future ProspectsCode1
TaskNorm: Rethinking Batch Normalization for Meta-LearningCode1
GlobalMamba: Global Image Serialization for Vision MambaCode1
A Spectral-Spatial-Dependent Global Learning Framework for Insufficient and Imbalanced Hyperspectral Image ClassificationCode1
Are These Birds Similar: Learning Branched Networks for Fine-grained RepresentationsCode1
Hyperspectral Image Classification Using Deep Matrix CapsulesCode1
iBOT: Image BERT Pre-Training with Online TokenizerCode1
Anytime Dense Prediction with Confidence AdaptivityCode1
Going deeper with Image TransformersCode1
Communication-Efficient Federated Learning Based on Explanation-Guided Pruning for Remote Sensing Image ClassificationCode1
Go Wider Instead of DeeperCode1
Confidence-aware multi-modality learning for eye disease screeningCode1
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based LocalizationCode1
Gradient-based Parameter Selection for Efficient Fine-TuningCode1
Gradient Matching for Domain GeneralizationCode1
Gradient-Guided Annealing for Domain GeneralizationCode1
Gradient Projection Memory for Continual LearningCode1
Graph Convolutional Networks for Hyperspectral Image ClassificationCode1
GradInit: Learning to Initialize Neural Networks for Stable and Efficient TrainingCode1
GradMA: A Gradient-Memory-based Accelerated Federated Learning with Alleviated Catastrophic ForgettingCode1
Can We Talk Models Into Seeing the World Differently?Code1
Graph Attention Transformer Network for Multi-Label Image ClassificationCode1
HyperKAN: Kolmogorov-Arnold Networks make Hyperspectral Image Classificators SmarterCode1
Hyperbolic Image-Text RepresentationsCode1
Hyperbolic Image EmbeddingsCode1
HyperDense-Net: A hyper-densely connected CNN for multi-modal image segmentationCode1
The Cascaded Forward Algorithm for Neural Network TrainingCode1
The CLEAR Benchmark: Continual LEArning on Real-World ImageryCode1
GRNN: Generative Regression Neural Network -- A Data Leakage Attack for Federated LearningCode1
Grid Saliency for Context Explanations of Semantic SegmentationCode1
Hyperspectral Band Selection for Multispectral Image Classification with Convolutional NetworksCode1
Grounded Situation Recognition with TransformersCode1
iDAT: inverse Distillation Adapter-TuningCode1
Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge DistillationCode1
Concurrent Spatial and Channel Squeeze & Excitation in Fully Convolutional NetworksCode1
Group Fisher Pruning for Practical Network CompressionCode1
The First to Know: How Token Distributions Reveal Hidden Knowledge in Large Vision-Language Models?Code1
The Heterogeneity Hypothesis: Finding Layer-Wise Differentiated Network ArchitecturesCode1
Learning Hierarchical Image Segmentation For Recognition and By RecognitionCode1
CondenseNet V2: Sparse Feature Reactivation for Deep NetworksCode1
Show:102550
← PrevPage 40 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