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 401425 of 10419 papers

TitleStatusHype
Conformer: Local Features Coupling Global Representations for Visual RecognitionCode1
Communication-Efficient Federated Learning Based on Explanation-Guided Pruning for Remote Sensing Image ClassificationCode1
Combining Human Predictions with Model Probabilities via Confusion Matrices and CalibrationCode1
Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge DistillationCode1
Combating Label Noise in Deep Learning Using AbstentionCode1
Combating noisy labels by agreement: A joint training method with co-regularizationCode1
3D U^2-Net: A 3D Universal U-Net for Multi-Domain Medical Image SegmentationCode1
A Rainbow in Deep Network Black BoxesCode1
Combining GANs and AutoEncoders for Efficient Anomaly DetectionCode1
Complementary-Label Learning for Arbitrary Losses and ModelsCode1
A Dual-Direction Attention Mixed Feature Network for Facial Expression RecognitionCode1
Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image EncodingCode1
Combining Metric Learning and Attention Heads For Accurate and Efficient Multilabel Image ClassificationCode1
Communication-Efficient and Privacy-Preserving Feature-based Federated Transfer LearningCode1
Co-Correcting: Noise-tolerant Medical Image Classification via mutual Label CorrectionCode1
CoCa: Contrastive Captioners are Image-Text Foundation ModelsCode1
An Open-source Tool for Hyperspectral Image Augmentation in TensorflowCode1
Are Natural Domain Foundation Models Useful for Medical Image Classification?Code1
ViViT: A Video Vision TransformerCode1
Are These Birds Similar: Learning Branched Networks for Fine-grained RepresentationsCode1
CODE-CL: Conceptor-Based Gradient Projection for Deep Continual LearningCode1
Advancing Vision Transformers with Group-Mix AttentionCode1
Approaching Deep Learning through the Spectral Dynamics of WeightsCode1
A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language ModelCode1
TransCenter: Transformers with Dense Representations for Multiple-Object TrackingCode1
Show:102550
← PrevPage 17 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