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 10261050 of 10419 papers

TitleStatusHype
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 42 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