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 10511075 of 10420 papers

TitleStatusHype
Bayesian Optimization Meets Self-DistillationCode1
DLME: Deep Local-flatness Manifold EmbeddingCode1
DLTTA: Dynamic Learning Rate for Test-time Adaptation on Cross-domain Medical ImagesCode1
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
DMT-JEPA: Discriminative Masked Targets for Joint-Embedding Predictive ArchitectureCode1
A Less Biased Evaluation of Out-of-distribution Sample DetectorsCode1
Divergences in Color Perception between Deep Neural Networks and HumansCode1
Bayesian continual learning and forgetting in neural networksCode1
Diverse Branch Block: Building a Convolution as an Inception-like UnitCode1
Distribution Alignment: A Unified Framework for Long-tail Visual RecognitionCode1
Bayesian Model-Agnostic Meta-LearningCode1
DiT: Self-supervised Pre-training for Document Image TransformerCode1
Diverse Sample Generation: Pushing the Limit of Generative Data-free QuantizationCode1
Distilling Object Detectors via Decoupled FeaturesCode1
Distilling Large Vision-Language Model with Out-of-Distribution GeneralizabilityCode1
Distilling Out-of-Distribution Robustness from Vision-Language Foundation ModelsCode1
Bayesian Neural Network Priors RevisitedCode1
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate ShiftCode1
Leveraging Vision-Language Models for Improving Domain Generalization in Image ClassificationCode1
Distilling Visual Priors from Self-Supervised LearningCode1
Diversified in-domain synthesis with efficient fine-tuning for few-shot classificationCode1
Do Input Gradients Highlight Discriminative Features?Code1
batchboost: regularization for stabilizing training with resistance to underfitting & overfittingCode1
Show:102550
← PrevPage 43 of 417Next →

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