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 31263150 of 10420 papers

TitleStatusHype
Video Pretraining Advances 3D Deep Learning on Chest CT TasksCode1
Multimodal Hyperspectral Image Classification via Interconnected Fusion0
ConvBLS: An Effective and Efficient Incremental Convolutional Broad Learning System for Image Classification0
Predictive Heterogeneity: Measures and Applications0
Vision Transformers with Mixed-Resolution TokenizationCode1
DIME-FM: DIstilling Multimodal and Efficient Foundation Models0
LaCViT: A Label-aware Contrastive Fine-tuning Framework for Vision TransformersCode0
Benchmarking FedAvg and FedCurv for Image Classification Tasks0
Rethinking Local Perception in Lightweight Vision TransformerCode1
PMatch: Paired Masked Image Modeling for Dense Geometric MatchingCode1
Soft Neighbors are Positive Supporters in Contrastive Visual Representation Learning0
Mole Recruitment: Poisoning of Image Classifiers via Selective Batch SamplingCode0
InceptionNeXt: When Inception Meets ConvNeXtCode4
Polarity is all you need to learn and transfer fasterCode0
Beyond Empirical Risk Minimization: Local Structure Preserving Regularization for Improving Adversarial Robustness0
Nearest Neighbor Based Out-of-Distribution Detection in Remote Sensing Scene Classification0
Towards Understanding the Effect of Pretraining Label Granularity0
Provable Robustness for Streaming Models with a Sliding Window0
On the Local Cache Update Rules in Streaming Federated Learning0
Fully Hyperbolic Convolutional Neural Networks for Computer VisionCode1
Your Diffusion Model is Secretly a Zero-Shot ClassifierCode2
Automated wildlife image classification: An active learning tool for ecological applicationsCode0
Iteratively Coupled Multiple Instance Learning from Instance to Bag Classifier for Whole Slide Image ClassificationCode1
Exploring Deep Learning Methods for Classification of SAR Images: Towards NextGen Convolutions via Transformers0
Learning Expressive Prompting With Residuals for Vision Transformers0
Show:102550
← PrevPage 126 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