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 87518800 of 10420 papers

TitleStatusHype
Dynamic Channel Selection in Self-Supervised LearningCode0
Ordinal Pooling Networks: For Preserving Information over Shrinking Feature MapsCode0
Compressing Deep CNNs using Basis Representation and Spectral Fine-tuningCode0
How Do Training Methods Influence the Utilization of Vision Models?Code0
Why Random Pruning Is All We Need to Start SparseCode0
How Flawed Is ECE? An Analysis via Logit SmoothingCode0
Quantifying contribution and propagation of error from computational steps, algorithms and hyperparameter choices in image classification pipelinesCode0
Dynamic 3D KAN Convolution with Adaptive Grid Optimization for Hyperspectral Image ClassificationCode0
Oriented Response NetworksCode0
Orthogonal Convolutional Neural NetworksCode0
Compress image to patches for Vision TransformerCode0
Orthogonal Deep Neural NetworksCode0
MIAFEx: An Attention-based Feature Extraction Method for Medical Image ClassificationCode0
Orthogonal Weight Normalization: Solution to Optimization over Multiple Dependent Stiefel Manifolds in Deep Neural NetworksCode0
Evolving Deep Neural Networks by Multi-objective Particle Swarm Optimization for Image ClassificationCode0
Compressed learning based onboard semantic compression for remote sensing platformsCode0
DyCE: Dynamically Configurable Exiting for Deep Learning Compression and Real-time ScalingCode0
OscNet v1.5: Energy Efficient Hopfield Network on CMOS Oscillators for Image ClassificationCode0
Dual-Task Vision Transformer for Rapid and Accurate Intracerebral Hemorrhage CT Image ClassificationCode0
VidModEx: Interpretable and Efficient Black Box Model Extraction for High-Dimensional SpacesCode0
Dual Path NetworksCode0
DualAug: Exploiting Additional Heavy Augmentation with OOD Data RejectionCode0
Dual Active Sampling on Batch-Incremental Active LearningCode0
How to Use Dropout Correctly on Residual Networks with Batch NormalizationCode0
Microscopic-Mamba: Revealing the Secrets of Microscopic Images with Just 4M ParametersCode0
Accelerating Training of Deep Neural Networks with a Standardization LossCode0
How transfer learning is used in generative models for image classification: improved accuracyCode0
DS_FusionNet: Dynamic Dual-Stream Fusion with Bidirectional Knowledge Distillation for Plant Disease RecognitionCode0
Accelerating Targeted Hard-Label Adversarial Attacks in Low-Query Black-Box SettingsCode0
DSD: Dense-Sparse-Dense Training for Deep Neural NetworksCode0
Drop to Adapt: Learning Discriminative Features for Unsupervised Domain AdaptationCode0
Dropout is NOT All You Need to Prevent Gradient LeakageCode0
DropBlock: A regularization method for convolutional networksCode0
Milking CowMask for Semi-Supervised Image ClassificationCode0
HSI-CNN: A Novel Convolution Neural Network for Hyperspectral ImageCode0
Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave ConvolutionCode0
Out-of-distribution Detection by Cross-class Vicinity Distribution of In-distribution DataCode0
MiMICRI: Towards Domain-centered Counterfactual Explanations of Cardiovascular Image Classification ModelsCode0
Quantile-based Maximum Likelihood Training for Outlier DetectionCode0
Compressed Learning: A Deep Neural Network ApproachCode0
Human Activity Recognition Based on Wearable Sensor Data: A Standardization of the State-of-the-ArtCode0
Adaptive Sample Selection for Robust Learning under Label NoiseCode0
Robust and accelerated single-spike spiking neural network training with applicability to challenging temporal tasksCode0
Min-Entropy Latent Model for Weakly Supervised Object DetectionCode0
Out-of-distribution forgetting: vulnerability of continual learning to intra-class distribution shiftCode0
Improving Deep Neural Network Classification Confidence using Heatmap-based eXplainable AICode0
Human-imperceptible, Machine-recognizable ImagesCode0
Drop Clause: Enhancing Performance, Interpretability and Robustness of the Tsetlin MachineCode0
Compound Figure Separation of Biomedical Images: Mining Large Datasets for Self-supervised LearningCode0
Human-in-the-Loop Visual Re-ID for Population Size EstimationCode0
Show:102550
← PrevPage 176 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