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 17511775 of 10420 papers

TitleStatusHype
Robust Instance Segmentation through Reasoning about Multi-Object OcclusionCode1
SuperLoss: A Generic Loss for Robust Curriculum LearningCode1
Disentangling Label Distribution for Long-tailed Visual RecognitionCode1
HRN: A Holistic Approach to One Class LearningCode1
Co-Tuning for Transfer LearningCode1
Is normalization indispensable for training deep neural network?Code1
Auto Learning AttentionCode1
Task-Oriented Feature DistillationCode1
Attention-Gated Brain Propagation: How the brain can implement reward-based error backpropagationCode1
Data Augmentation with norm-VAE for Unsupervised Domain AdaptationCode1
Towards Better Accuracy-efficiency Trade-offs: Divide and Co-trainingCode1
BSNet: Bi-Similarity Network for Few-shot Fine-grained Image ClassificationCode1
ProtoPShare: Prototype Sharing for Interpretable Image Classification and Similarity DiscoveryCode1
General Multi-label Image Classification with TransformersCode1
How Well Do Self-Supervised Models Transfer?Code1
Regularization with Latent Space Virtual Adversarial TrainingCode1
Match Them Up: Visually Explainable Few-shot Image ClassificationCode1
No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification ProblemsCode1
Mixture-based Feature Space Learning for Few-shot Image ClassificationCode1
KeepAugment: A Simple Information-Preserving Data Augmentation ApproachCode1
Head Network Distillation: Splitting Distilled Deep Neural Networks for Resource-Constrained Edge Computing SystemsCode1
Error-Bounded Correction of Noisy LabelsCode1
Geography-Aware Self-Supervised LearningCode1
Dense Contrastive Learning for Self-Supervised Visual Pre-TrainingCode1
Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive LearningCode1
Show:102550
← PrevPage 71 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
5DaViT-HTop 1 Accuracy90.2Unverified
6Meta Pseudo Labels (EfficientNet-L2)Top 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