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 10011050 of 10419 papers

TitleStatusHype
Improving the Computer-Aided Estimation of Ulcerative Colitis Severity According to Mayo Endoscopic Score by Using Regression-Based Deep LearningCode1
Improving the Resolution of CNN Feature Maps Efficiently with MultisamplingCode1
Curriculum By SmoothingCode1
Convolutional Xformers for VisionCode1
Improving Zero-shot Generalization and Robustness of Multi-modal ModelsCode1
IncepFormer: Efficient Inception Transformer with Pyramid Pooling for Semantic SegmentationCode1
A Fast Knowledge Distillation Framework for Visual RecognitionCode1
Balanced Contrastive Learning for Long-Tailed Visual RecognitionCode1
Counterfactual Explanations for Medical Image Classification and Regression using Diffusion AutoencoderCode1
Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuningCode1
ACPL: Anti-curriculum Pseudo-labelling for Semi-supervised Medical Image ClassificationCode1
InfoMatch: Entropy Neural Estimation for Semi-Supervised Image ClassificationCode1
Information Maximization Clustering via Multi-View Self-LabellingCode1
InsPLAD: A Dataset and Benchmark for Power Line Asset Inspection in UAV ImagesCode1
Convolutional Spiking Neural Networks for Spatio-Temporal Feature ExtractionCode1
Convolution-enhanced Evolving Attention NetworksCode1
Integrated Image and Location Analysis for Wound Classification: A Deep Learning ApproachCode1
Interferometric Graph Transform: a Deep Unsupervised Graph RepresentationCode1
A Second-Order Approach to Learning with Instance-Dependent Label NoiseCode1
Interpolation between Residual and Non-Residual NetworksCode1
Balanced Energy Regularization Loss for Out-of-distribution DetectionCode1
Convolutional Channel-wise Competitive Learning for the Forward-Forward AlgorithmCode1
ConvMLP: Hierarchical Convolutional MLPs for VisionCode1
Convolutional Sequence to Sequence LearningCode1
CoProNN: Concept-based Prototypical Nearest Neighbors for Explaining Vision ModelsCode1
Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy LabelsCode1
Contrastive Masked Autoencoders are Stronger Vision LearnersCode1
Controllable Orthogonalization in Training DNNsCode1
Contrastive Losses Are Natural Criteria for Unsupervised Video SummarizationCode1
CorGAN: Correlation-Capturing Convolutional Generative Adversarial Networks for Generating Synthetic Healthcare RecordsCode1
Contrastive Learning Improves Model Robustness Under Label NoiseCode1
Contrastive Learning of Generalized Game RepresentationsCode1
Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional UnderstandingCode1
ConTNet: Why not use convolution and transformer at the same time?Code1
Contrastive Deep SupervisionCode1
Contrastive Learning of Medical Visual Representations from Paired Images and TextCode1
Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse DataCode1
Adapting Grad-CAM for Embedding NetworksCode1
Continual Learning Using a Kernel-Based Method Over Foundation ModelsCode1
A survey on attention mechanisms for medical applications: are we moving towards better algorithms?Code1
Algorithm-hardware Co-design for Deformable ConvolutionCode1
Continual Hippocampus Segmentation with TransformersCode1
Continual Learning with Scaled Gradient ProjectionCode1
CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasksCode1
Curriculum Labeling: Revisiting Pseudo-Labeling for Semi-Supervised LearningCode1
Contextual Convolutional Neural NetworksCode1
Contextual Diversity for Active LearningCode1
Content-aware Token Sharing for Efficient Semantic Segmentation with Vision TransformersCode1
Contextual Squeeze-and-Excitation for Efficient Few-Shot Image ClassificationCode1
Conformer: Local Features Coupling Global Representations for Visual RecognitionCode1
Show:102550
← PrevPage 21 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