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 551600 of 10419 papers

TitleStatusHype
Confidence-aware multi-modality learning for eye disease screeningCode1
Anytime Dense Prediction with Confidence AdaptivityCode1
Confidence Regularized Self-TrainingCode1
Concurrent Spatial and Channel Squeeze & Excitation in Fully Convolutional NetworksCode1
Learning Hierarchical Image Segmentation For Recognition and By RecognitionCode1
CondenseNet V2: Sparse Feature Reactivation for Deep NetworksCode1
Conformer: Local Features Coupling Global Representations for Visual RecognitionCode1
Compressing Features for Learning with Noisy LabelsCode1
AdaViT: Adaptive Tokens for Efficient Vision TransformerCode1
Compressive Visual RepresentationsCode1
Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural NetworkCode1
The MAMe Dataset: On the relevance of High Resolution and Variable Shape image propertiesCode1
Stateful ODE-Nets using Basis Function ExpansionsCode1
Concept Learners for Few-Shot LearningCode1
Consistency-based Active Learning for Object DetectionCode1
Continual Hippocampus Segmentation with TransformersCode1
A Data Set and a Convolutional Model for Iconography Classification in PaintingsCode1
Communication-Efficient and Privacy-Preserving Feature-based Federated Transfer LearningCode1
Communication-Efficient Federated Learning Based on Explanation-Guided Pruning for Remote Sensing Image ClassificationCode1
AdaScale SGD: A User-Friendly Algorithm for Distributed TrainingCode1
Combining Human Predictions with Model Probabilities via Confusion Matrices and CalibrationCode1
Combining Metric Learning and Attention Heads For Accurate and Efficient Multilabel Image ClassificationCode1
Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge DistillationCode1
Combating Label Noise in Deep Learning Using AbstentionCode1
Collaborative Transformers for Grounded Situation RecognitionCode1
Combating noisy labels by agreement: A joint training method with co-regularizationCode1
CODE-CL: Conceptor-Based Gradient Projection for Deep Continual LearningCode1
CoDeNet: Efficient Deployment of Input-Adaptive Object Detection on Embedded FPGAsCode1
Combining GANs and AutoEncoders for Efficient Anomaly DetectionCode1
Complementary-Label Learning for Arbitrary Losses and ModelsCode1
Co2L: Contrastive Continual LearningCode1
Co^2L: Contrastive Continual LearningCode1
CoAtNet: Marrying Convolution and Attention for All Data SizesCode1
CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep LearningCode1
Adaptive Split-Fusion TransformerCode1
CNN Filter DB: An Empirical Investigation of Trained Convolutional FiltersCode1
CoCa: Contrastive Captioners are Image-Text Foundation ModelsCode1
Clusterability as an Alternative to Anchor Points When Learning with Noisy LabelsCode1
ClusterFormer: Clustering As A Universal Visual LearnerCode1
Learning Loss for Active LearningCode1
CLR: Channel-wise Lightweight Reprogramming for Continual LearningCode1
Cluster-to-Conquer: A Framework for End-to-End Multi-Instance Learning for Whole Slide Image ClassificationCode1
Co-Correcting: Noise-tolerant Medical Image Classification via mutual Label CorrectionCode1
Compositional Explanations of NeuronsCode1
Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse DataCode1
CLIP meets DINO for Tuning Zero-Shot Classifier using Unlabeled Image CollectionsCode1
CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object NavigationCode1
Adaptive Risk Minimization: Learning to Adapt to Domain ShiftCode1
CLIP-guided Federated Learning on Heterogeneous and Long-Tailed DataCode1
Clean-Label Backdoor Attacks on Video Recognition ModelsCode1
Show:102550
← PrevPage 12 of 209Next →

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