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 20262050 of 10420 papers

TitleStatusHype
HMIL: Hierarchical Multi-Instance Learning for Fine-Grained Whole Slide Image ClassificationCode1
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnessCode1
Consistency-based Active Learning for Object DetectionCode1
How Does Pruning Impact Long-Tailed Multi-Label Medical Image Classifiers?Code1
Towards Uncovering the Intrinsic Data Structures for Unsupervised Domain Adaptation using Structurally Regularized Deep ClusteringCode1
How to Learn More? Exploring Kolmogorov-Arnold Networks for Hyperspectral Image ClassificationCode1
Shallow-Deep Networks: Understanding and Mitigating Network OverthinkingCode1
Image Representations Learned With Unsupervised Pre-Training Contain Human-like BiasesCode1
ImageNet-21K Pretraining for the MassesCode1
How to train your ViT? Data, Augmentation, and Regularization in Vision TransformersCode1
Trainable Noise Model as an XAI evaluation method: application on Sobol for remote sensing image segmentationCode1
Stateful ODE-Nets using Basis Function ExpansionsCode1
Compressing Features for Learning with Noisy LabelsCode1
Image-free Classifier Injection for Zero-Shot ClassificationCode1
HRFormer: High-Resolution Transformer for Dense PredictionCode1
HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight TransformersCode1
HRN: A Holistic Approach to One Class LearningCode1
Training objective drives the consistency of representational similarity across datasetsCode1
Compressive Visual RepresentationsCode1
ImageNet Large Scale Visual Recognition ChallengeCode1
HS-ResNet: Hierarchical-Split Block on Convolutional Neural NetworkCode1
Image sensing with multilayer, nonlinear optical neural networksCode1
Image Classification with Small Datasets: Overview and BenchmarkCode1
Conformer: Local Features Coupling Global Representations for Visual RecognitionCode1
Image Clustering with External GuidanceCode1
Show:102550
← PrevPage 82 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