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 20512100 of 10419 papers

TitleStatusHype
Improving Visual Prompt Tuning for Self-supervised Vision TransformersCode1
Improving Visual Recognition with Hyperbolical Visual Hierarchy MappingCode1
Improving Object Detection by Label Assignment DistillationCode1
Improving Medical Image Classification in Noisy Labels Using Only Self-supervised PretrainingCode1
Improving robustness against common corruptions by covariate shift adaptationCode1
Contrastive Deep SupervisionCode1
Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional UnderstandingCode1
Improving GAN Training via Feature Space ShrinkageCode1
Improving Self-Organizing Maps with Unsupervised Feature ExtractionCode1
Improving Zero-shot Generalization and Robustness of Multi-modal ModelsCode1
Instance Similarity Learning for Unsupervised Feature RepresentationCode1
Improving accuracy and speeding up Document Image Classification through parallel systemsCode1
Vision Transformers with Patch DiversificationCode1
Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?Code1
Continual Hippocampus Segmentation with TransformersCode1
A Simple Semi-Supervised Learning Framework for Object DetectionCode1
Improved Regularization of Convolutional Neural Networks with CutoutCode1
A Simple Interpretable Transformer for Fine-Grained Image Classification and AnalysisCode1
Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse DataCode1
Improved Residual Networks for Image and Video RecognitionCode1
Improving Cross-domain Few-shot Classification with Multilayer PerceptronCode1
Contextual Transformer Networks for Visual RecognitionCode1
Continual atlas-based segmentation of prostate MRICode1
Contextual Squeeze-and-Excitation for Efficient Few-Shot Image ClassificationCode1
Improved Zero-Shot Classification by Adapting VLMs with Text DescriptionsCode1
Improve Object Detection with Feature-based Knowledge Distillation: Towards Accurate and Efficient DetectorsCode1
Anytime Dense Prediction with Confidence AdaptivityCode1
Continual Learning Using a Kernel-Based Method Over Foundation ModelsCode1
Confidence-aware multi-modality learning for eye disease screeningCode1
A&B BNN: Add&Bit-Operation-Only Hardware-Friendly Binary Neural NetworkCode1
A Single Graph Convolution Is All You Need: Efficient Grayscale Image ClassificationCode1
ConTNet: Why not use convolution and transformer at the same time?Code1
Improving Generalization in Federated Learning by Seeking Flat MinimaCode1
IMAE for Noise-Robust Learning: Mean Absolute Error Does Not Treat Examples Equally and Gradient Magnitude's Variance MattersCode1
Improving neural networks by preventing co-adaptation of feature detectorsCode1
Confidence Regularized Self-TrainingCode1
Contrastive Learning Improves Model Robustness Under Label NoiseCode1
Controllable Orthogonalization in Training DNNsCode1
Improving the Resolution of CNN Feature Maps Efficiently with MultisamplingCode1
Conformer: Local Features Coupling Global Representations for Visual RecognitionCode1
Improved Online Conformal Prediction via Strongly Adaptive Online LearningCode1
Contrastive Learning of Generalized Game RepresentationsCode1
Improved Generation of Adversarial Examples Against Safety-aligned LLMsCode1
Contrastive Losses Are Natural Criteria for Unsupervised Video SummarizationCode1
A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data AugmentationCode1
IncepFormer: Efficient Inception Transformer with Pyramid Pooling for Semantic SegmentationCode1
MViTv2: Improved Multiscale Vision Transformers for Classification and DetectionCode1
A Simple Baseline for Low-Budget Active LearningCode1
ConvMLP: Hierarchical Convolutional MLPs for VisionCode1
CondenseNet V2: Sparse Feature Reactivation for Deep NetworksCode1
Show:102550
← PrevPage 42 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