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 401450 of 10419 papers

TitleStatusHype
FocusNet: Classifying Better by Focusing on Confusing ClassesCode1
Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image EncodingCode1
A Dual-Direction Attention Mixed Feature Network for Facial Expression RecognitionCode1
CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object NavigationCode1
3D U^2-Net: A 3D Universal U-Net for Multi-Domain Medical Image SegmentationCode1
CLIP meets DINO for Tuning Zero-Shot Classifier using Unlabeled Image CollectionsCode1
CLR: Channel-wise Lightweight Reprogramming for Continual LearningCode1
CleanNet: Transfer Learning for Scalable Image Classifier Training with Label NoiseCode1
Clean-Label Backdoor Attacks on Video Recognition ModelsCode1
CLIP4IDC: CLIP for Image Difference CaptioningCode1
CLCC: Contrastive Learning for Color ConstancyCode1
TransCenter: Transformers with Dense Representations for Multiple-Object TrackingCode1
CLCNet: Rethinking of Ensemble Modeling with Classification Confidence NetworkCode1
CLIP the Gap: A Single Domain Generalization Approach for Object DetectionCode1
4-bit Shampoo for Memory-Efficient Network TrainingCode1
ClusterFormer: Clustering As A Universal Visual LearnerCode1
An Open-source Tool for Hyperspectral Image Augmentation in TensorflowCode1
CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep LearningCode1
ViViT: A Video Vision TransformerCode1
Co2L: Contrastive Continual LearningCode1
Class Distance Weighted Cross-Entropy Loss for Ulcerative Colitis Severity EstimationCode1
Advancing Vision Transformers with Group-Mix AttentionCode1
Advantages and Bottlenecks of Quantum Machine Learning for Remote SensingCode1
A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language ModelCode1
Collaborative Transformers for Grounded Situation RecognitionCode1
AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive LearningCode1
Combining GANs and AutoEncoders for Efficient Anomaly DetectionCode1
Combining Human Predictions with Model Probabilities via Confusion Matrices and CalibrationCode1
A Comprehensive Approach to Unsupervised Embedding Learning based on AND AlgorithmCode1
Communication-Efficient and Privacy-Preserving Feature-based Federated Transfer LearningCode1
Class-Difficulty Based Methods for Long-Tailed Visual RecognitionCode1
Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual UnderstandingCode1
A Comprehensive Empirical Evaluation on Online Continual LearningCode1
Stateful ODE-Nets using Basis Function ExpansionsCode1
AGI-Elo: How Far Are We From Mastering A Task?Code1
Concept Learners for Few-Shot LearningCode1
Concurrent Spatial and Channel Squeeze & Excitation in Fully Convolutional NetworksCode1
CondenseNet V2: Sparse Feature Reactivation for Deep NetworksCode1
Conformer: Local Features Coupling Global Representations for Visual RecognitionCode1
Consistency-based Active Learning for Object DetectionCode1
Optimized spiking neurons classify images with high accuracy through temporal coding with two spikesCode1
Adversarial Attacks on ML Defense Models CompetitionCode1
Benchmarking Pathology Feature Extractors for Whole Slide Image ClassificationCode1
Contextual Diversity for Active LearningCode1
A General Regret Bound of Preconditioned Gradient Method for DNN TrainingCode1
Continual atlas-based segmentation of prostate MRICode1
Class-Balanced Loss Based on Effective Number of SamplesCode1
Adversarial AutoMixupCode1
Contrastive Deep SupervisionCode1
Class-Incremental Grouping Network for Continual Audio-Visual LearningCode1
Show:102550
← PrevPage 9 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