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 426450 of 10419 papers

TitleStatusHype
TransCenter: Transformers with Dense Representations for Multiple-Object TrackingCode1
Concept Learners for Few-Shot LearningCode1
Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse DataCode1
A Comprehensive Approach to Unsupervised Embedding Learning based on AND AlgorithmCode1
A Simple Baseline for Low-Budget Active LearningCode1
Complementary-Label Learning for Arbitrary Losses and ModelsCode1
Can We Talk Models Into Seeing the World Differently?Code1
A Comprehensive Empirical Evaluation on Online Continual LearningCode1
A Simple Semi-Supervised Learning Framework for Object DetectionCode1
A Spectral-Spatial-Dependent Global Learning Framework for Insufficient and Imbalanced Hyperspectral Image ClassificationCode1
Contrastive Learning of Generalized Game RepresentationsCode1
Compositional Explanations of NeuronsCode1
Contrastive Losses Are Natural Criteria for Unsupervised Video SummarizationCode1
A Survey on Transferability of Adversarial Examples across Deep Neural NetworksCode1
AQD: Towards Accurate Fully-Quantized Object DetectionCode1
A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network CalibrationCode1
Adversarial Attacks on ML Defense Models CompetitionCode1
Astroformer: More Data Might not be all you need for ClassificationCode1
A Survey: Deep Learning for Hyperspectral Image Classification with Few Labeled SamplesCode1
A survey on attention mechanisms for medical applications: are we moving towards better algorithms?Code1
Arch-Net: Model Distillation for Architecture Agnostic Model DeploymentCode1
Embedded Prompt Tuning: Towards Enhanced Calibration of Pretrained Models for Medical ImagesCode1
Adversarial AutoMixupCode1
AsymmNet: Towards ultralight convolution neural networks using asymmetrical bottlenecksCode1
Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural NetworkCode1
Show:102550
← PrevPage 18 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