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 701750 of 10419 papers

TitleStatusHype
DIANet: Dense-and-Implicit Attention NetworkCode1
Analysis and evaluation of Deep Learning based Super-Resolution algorithms to improve performance in Low-Resolution Face RecognitionCode1
DecoupleNet: A Lightweight Backbone Network With Efficient Feature Decoupling for Remote Sensing Visual TasksCode1
Balanced Contrastive Learning for Long-Tailed Visual RecognitionCode1
Deep AutoAugmentCode1
Diffusion Mechanism in Residual Neural Network: Theory and ApplicationsCode1
Augmentation Strategies for Learning with Noisy LabelsCode1
Balanced-MixUp for Highly Imbalanced Medical Image ClassificationCode1
Barlow Twins: Self-Supervised Learning via Redundancy ReductionCode1
batchboost: regularization for stabilizing training with resistance to underfitting & overfittingCode1
Adaptive Split-Fusion TransformerCode1
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate ShiftCode1
Augmented Neural Fine-Tuning for Efficient Backdoor PurificationCode1
BinaryViT: Pushing Binary Vision Transformers Towards Convolutional ModelsCode1
Bayesian continual learning and forgetting in neural networksCode1
Bayesian Neural Network Priors RevisitedCode1
DiG-IN: Diffusion Guidance for Investigating Networks -- Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual ExplanationsCode1
Bayesian Model-Agnostic Meta-LearningCode1
DeepEMD: Differentiable Earth Mover's Distance for Few-Shot LearningCode1
Bayesian Optimization Meets Self-DistillationCode1
Benchmarking Adversarial Robustness on Image ClassificationCode1
Better plain ViT baselines for ImageNet-1kCode1
Discrimination-aware Network Pruning for Deep Model CompressionCode1
Analyzing Vision Transformers for Image Classification in Class Embedding SpaceCode1
Deep-Learning-Based Aerial Image Classification for Emergency Response Applications Using Unmanned Aerial VehiclesCode1
Disentangle and Remerge: Interventional Knowledge Distillation for Few-Shot Object Detection from A Conditional Causal PerspectiveCode1
Benchmarking Bias Mitigation Algorithms in Representation Learning through Fairness MetricsCode1
Distilled Split Deep Neural Networks for Edge-Assisted Real-Time SystemsCode1
AdaScale SGD: A User-Friendly Algorithm for Distributed TrainingCode1
An Analysis on Ensemble Learning optimized Medical Image Classification with Deep Convolutional Neural NetworksCode1
Distilling Out-of-Distribution Robustness from Vision-Language Foundation ModelsCode1
Distilling Visual Priors from Self-Supervised LearningCode1
DeepViT: Towards Deeper Vision TransformerCode1
Benchmarking Test-Time Adaptation against Distribution Shifts in Image ClassificationCode1
The MAMe Dataset: On the relevance of High Resolution and Variable Shape image propertiesCode1
DiffMIC: Dual-Guidance Diffusion Network for Medical Image ClassificationCode1
BEV-LGKD: A Unified LiDAR-Guided Knowledge Distillation Framework for BEV 3D Object DetectionCode1
Beyond Categorical Label Representations for Image ClassificationCode1
Do You Even Need Attention? A Stack of Feed-Forward Layers Does Surprisingly Well on ImageNetCode1
Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label NoiseCode1
Beyond Gradient Averaging in Parallel Optimization: Improved Robustness through Gradient Agreement FilteringCode1
DivideMix: Learning with Noisy Labels as Semi-supervised LearningCode1
Revisiting the Importance of Amplifying Bias for DebiasingCode1
Attentive WaveBlock: Complementarity-enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-identification and BeyondCode1
DMT-JEPA: Discriminative Masked Targets for Joint-Embedding Predictive ArchitectureCode1
DO-Conv: Depthwise Over-parameterized Convolutional LayerCode1
Bias Loss for Mobile Neural NetworksCode1
Bi-directional Feature Reconstruction Network for Fine-Grained Few-Shot Image ClassificationCode1
BiasPruner: Debiased Continual Learning for Medical Image ClassificationCode1
Attentive Weights Generation for Few Shot Learning via Information MaximizationCode1
Show:102550
← PrevPage 15 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