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 14011425 of 10420 papers

TitleStatusHype
Information Bottleneck Approach to Spatial Attention LearningCode1
Unifying Nonlocal Blocks for Neural NetworksCode1
Instance Similarity Learning for Unsupervised Feature RepresentationCode1
Generic Neural Architecture Search via RegressionCode1
Vision Transformer with Progressive SamplingCode1
Toward Improving Confidence in Autonomous Vehicle Software: A Study on Traffic Sign Recognition SystemsCode1
Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision TransformerCode1
Domain Generalization via Gradient SurgeryCode1
Group Fisher Pruning for Practical Network CompressionCode1
CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale AttentionCode1
A New Semi-supervised Learning Benchmark for Classifying View and Diagnosing Aortic Stenosis from EchocardiogramsCode1
DPT: Deformable Patch-based Transformer for Visual RecognitionCode1
Semi-Supervised Active Learning with Temporal Output DiscrepancyCode1
Self-Supervised Learning for Fine-Grained Image ClassificationCode1
Towards robust vision by multi-task learning on monkey visual cortexCode1
Self-Paced Contrastive Learning for Semi-supervised Medical Image Segmentation with Meta-labelsCode1
WaveCNet: Wavelet Integrated CNNs to Suppress Aliasing Effect for Noise-Robust Image ClassificationCode1
AASAE: Augmentation-Augmented Stochastic AutoencodersCode1
Contextual Transformer Networks for Visual RecognitionCode1
Parametric Contrastive LearningCode1
Go Wider Instead of DeeperCode1
Leveraging Auxiliary Tasks with Affinity Learning for Weakly Supervised Semantic SegmentationCode1
Bias Loss for Mobile Neural NetworksCode1
Photon-Starved Scene Inference using Single Photon CamerasCode1
CycleMLP: A MLP-like Architecture for Dense PredictionCode1
Show:102550
← PrevPage 57 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