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 12011250 of 10419 papers

TitleStatusHype
Augmented Neural ODEsCode1
Augmenting Convolutional networks with attention-based aggregationCode1
Balanced Energy Regularization Loss for Out-of-distribution DetectionCode1
Differentiable Model Compression via Pseudo Quantization NoiseCode1
Balanced Contrastive Learning for Long-Tailed Visual RecognitionCode1
Differentiable Top-k Classification LearningCode1
Abstracting Deep Neural Networks into Concept Graphs for Concept Level InterpretabilityCode1
CorGAN: Correlation-Capturing Convolutional Generative Adversarial Networks for Generating Synthetic Healthcare RecordsCode1
Co-Tuning for Transfer LearningCode1
Diffusion Model as Representation LearnerCode1
CrAM: A Compression-Aware MinimizerCode1
AugMix: A Simple Data Processing Method to Improve Robustness and UncertaintyCode1
A Survey on Transferability of Adversarial Examples across Deep Neural NetworksCode1
Dilated convolution with learnable spacingsCode1
Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual UnderstandingCode1
batchboost: regularization for stabilizing training with resistance to underfitting & overfittingCode1
A Unified Algebraic Perspective on Lipschitz Neural NetworksCode1
On Creating Benchmark Dataset for Aerial Image Interpretation: Reviews, Guidances and Million-AIDCode1
Adapting Grad-CAM for Embedding NetworksCode1
Discretization-Aware Architecture SearchCode1
Discriminator-free Unsupervised Domain Adaptation for Multi-label Image ClassificationCode1
Disentangle and Remerge: Interventional Knowledge Distillation for Few-Shot Object Detection from A Conditional Causal PerspectiveCode1
Distilled Split Deep Neural Networks for Edge-Assisted Real-Time SystemsCode1
Leveraging Vision-Language Models for Improving Domain Generalization in Image ClassificationCode1
Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine SynergyCode1
Distilling Object Detectors via Decoupled FeaturesCode1
Barlow Twins: Self-Supervised Learning via Redundancy ReductionCode1
Distribution Alignment: A Unified Framework for Long-tail Visual RecognitionCode1
Divergences in Color Perception between Deep Neural Networks and HumansCode1
A Universal Representation Transformer Layer for Few-Shot Image ClassificationCode1
Convolutional Spiking Neural Networks for Spatio-Temporal Feature ExtractionCode1
Convolutional Channel-wise Competitive Learning for the Forward-Forward AlgorithmCode1
Convolutional Sequence to Sequence LearningCode1
DKDFN: Domain Knowledge-Guided deep collaborative fusion network for multimodal unitemporal remote sensing land cover classificationCode1
Convolutional Xformers for VisionCode1
AutoDC: Automated data-centric processingCode1
DO-Conv: Depthwise Over-parameterized Convolutional LayerCode1
AutoDiCE: Fully Automated Distributed CNN Inference at the EdgeCode1
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate ShiftCode1
A Less Biased Evaluation of Out-of-distribution Sample DetectorsCode1
Domain Adaptation for Multi-label Image Classification: a Discriminator-free ApproachCode1
Controllable Orthogonalization in Training DNNsCode1
Domain Generalization via Gradient SurgeryCode1
Do text-free diffusion models learn discriminative visual representations?Code1
Auto Learning AttentionCode1
AutoLRS: Automatic Learning-Rate Schedule by Bayesian Optimization on the FlyCode1
DPMLBench: Holistic Evaluation of Differentially Private Machine LearningCode1
DPT: Deformable Patch-based Transformer for Visual RecognitionCode1
Automated detection of COVID-19 cases from chest X-ray images using deep neural network and XGBoostCode1
A Bregman Learning Framework for Sparse Neural NetworksCode1
Show:102550
← PrevPage 25 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