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 10511075 of 10419 papers

TitleStatusHype
Convolutional Spiking Neural Networks for Spatio-Temporal Feature ExtractionCode1
Contrastive Masked Autoencoders are Stronger Vision LearnersCode1
Contrastive Losses Are Natural Criteria for Unsupervised Video SummarizationCode1
Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy LabelsCode1
Contrastive Learning of Medical Visual Representations from Paired Images and TextCode1
AsymmNet: Towards ultralight convolution neural networks using asymmetrical bottlenecksCode1
Controllable Orthogonalization in Training DNNsCode1
Convolutional Xformers for VisionCode1
Contrastive Deep SupervisionCode1
Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional UnderstandingCode1
Contrastive Learning Improves Model Robustness Under Label NoiseCode1
Continual Learning with Scaled Gradient ProjectionCode1
Asymmetric Loss For Multi-Label ClassificationCode1
ConTNet: Why not use convolution and transformer at the same time?Code1
Continual Hippocampus Segmentation with TransformersCode1
Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse DataCode1
Contextual Transformer Networks for Visual RecognitionCode1
Asymmetric Polynomial Loss For Multi-Label ClassificationCode1
Continual atlas-based segmentation of prostate MRICode1
Continual Learning Using a Kernel-Based Method Over Foundation ModelsCode1
Contrastive Learning of Generalized Game RepresentationsCode1
Convolution-enhanced Evolving Attention NetworksCode1
Content-aware Token Sharing for Efficient Semantic Segmentation with Vision TransformersCode1
Consistency-based Active Learning for Object DetectionCode1
Conformer: Local Features Coupling Global Representations for Visual RecognitionCode1
Show:102550
← PrevPage 43 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