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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1001–1050 of 10419 papers

TitleStatusHype
DMT-JEPA: Discriminative Masked Targets for Joint-Embedding Predictive ArchitectureCode1
DATA: Domain-Aware and Task-Aware Self-supervised LearningCode1
A Robust Feature Downsampling Module for Remote Sensing Visual TasksCode1
Data-Efficient Deep Learning Method for Image Classification Using Data Augmentation, Focal Cosine Loss, and EnsembleCode1
Data Feedback Loops: Model-driven Amplification of Dataset BiasesCode1
Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuningCode1
DLTTA: Dynamic Learning Rate for Test-time Adaptation on Cross-domain Medical ImagesCode1
DataMUX: Data Multiplexing for Neural NetworksCode1
Counterfactual Explanations for Medical Image Classification and Regression using Diffusion AutoencoderCode1
DEAL: Deep Evidential Active Learning for Image ClassificationCode1
ACPL: Anti-curriculum Pseudo-labelling for Semi-supervised Medical Image ClassificationCode1
Instance-Conditional Knowledge Distillation for Object DetectionCode1
Dataset Condensation with Contrastive SignalsCode1
Instance Localization for Self-supervised Detection PretrainingCode1
DO-Conv: Depthwise Over-parameterized Convolutional LayerCode1
Bayesian Model-Agnostic Meta-LearningCode1
Bayesian Neural Network Priors RevisitedCode1
InterLUDE: Interactions between Labeled and Unlabeled Data to Enhance Semi-Supervised LearningCode1
A Second-Order Approach to Learning with Instance-Dependent Label NoiseCode1
DCN-T: Dual Context Network with Transformer for Hyperspectral Image ClassificationCode1
DCT-CryptoNets: Scaling Private Inference in the Frequency DomainCode1
Bayesian Optimization Meets Self-DistillationCode1
DocXClassifier: High Performance Explainable Deep Network for Document Image ClassificationCode1
DivideMix: Learning with Noisy Labels as Semi-supervised LearningCode1
Diversify and Disambiguate: Learning From Underspecified DataCode1
DKDFN: Domain Knowledge-Guided deep collaborative fusion network for multimodal unitemporal remote sensing land cover classificationCode1
Bayesian continual learning and forgetting in neural networksCode1
DLME: Deep Local-flatness Manifold EmbeddingCode1
Do Deep Networks Transfer Invariances Across Classes?Code1
Divergences in Color Perception between Deep Neural Networks and HumansCode1
DiT: Self-supervised Pre-training for Document Image TransformerCode1
Diverse Branch Block: Building a Convolution as an Inception-like UnitCode1
batchboost: regularization for stabilizing training with resistance to underfitting & overfittingCode1
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate ShiftCode1
Diverse Sample Generation: Pushing the Limit of Generative Data-free QuantizationCode1
Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine SynergyCode1
Adapting Grad-CAM for Embedding NetworksCode1
Barlow Twins: Self-Supervised Learning via Redundancy ReductionCode1
Distilling Out-of-Distribution Robustness from Vision-Language Foundation ModelsCode1
Algorithm-hardware Co-design for Deformable ConvolutionCode1
Distilling Visual Priors from Self-Supervised LearningCode1
Distribution Alignment: A Unified Framework for Long-tail Visual RecognitionCode1
Diversified in-domain synthesis with efficient fine-tuning for few-shot classificationCode1
Does VLM Classification Benefit from LLM Description Semantics?Code1
DualConv: Dual Convolutional Kernels for Lightweight Deep Neural NetworksCode1
Balanced Contrastive Learning for Long-Tailed Visual RecognitionCode1
Disentangling Label Distribution for Long-tailed Visual RecognitionCode1
Balanced Energy Regularization Loss for Out-of-distribution DetectionCode1
Disentangled Ontology Embedding for Zero-shot LearningCode1
Distilled Split Deep Neural Networks for Edge-Assisted Real-Time SystemsCode1
Show:102550
← PrevPage 21 of 209Next →
All datasetsImageNetCIFAR-10CIFAR-100STL-10ObjectNetMNISTSVHNiNaturalist 2018ImageNet ReaLFlowers-102Clothing1Mmini WebVision 1.0

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CoCa (finetuned)Top 1 Accuracy91—Unverified
2Model soups (BASIC-L)Top 1 Accuracy90.98—Unverified
3Model soups (ViT-G/14)Top 1 Accuracy90.94—Unverified
4DaViT-GTop 1 Accuracy90.4—Unverified
5DaViT-HTop 1 Accuracy90.2—Unverified
6Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2—Unverified
7SwinV2-GTop 1 Accuracy90.17—Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1—Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05—Unverified
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90—Unverified