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 56265650 of 10420 papers

TitleStatusHype
Go Wider Instead of DeeperCode1
An Uncertainty-Aware Deep Learning Framework for Defect Detection in Casting Products0
Multi-Label Image Classification with Contrastive Learning0
Reconstructing Images of Two Adjacent Objects through Scattering Medium Using Generative Adversarial Network0
Compositional Models: Multi-Task Learning and Knowledge Transfer with Modular Networks0
Photon-Starved Scene Inference using Single Photon CamerasCode1
Pruning Ternary Quantization0
Bias Loss for Mobile Neural NetworksCode1
RGB Image Classification with Quantum Convolutional Ansaetze0
MCDAL: Maximum Classifier Discrepancy for Active LearningCode0
Rethinking Hard-Parameter Sharing in Multi-Domain Learning0
Federated Learning Versus Classical Machine Learning: A Convergence Comparison0
Bridging the Gap between Spatial and Spectral Domains: A Unified Framework for Graph Neural NetworksCode1
CycleMLP: A MLP-like Architecture for Dense PredictionCode1
Precision-Weighted Federated Learning0
Understanding Gender and Racial Disparities in Image Recognition Models0
Parametric Scattering NetworksCode1
Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed RecognitionCode1
Protecting Semantic Segmentation Models by Using Block-wise Image Encryption with Secret Key from Unauthorized Access0
A New Clustering-Based Technique for the Acceleration of Deep Convolutional Networks0
Non-binary deep transfer learning for image classificationCode1
CHEF: A Cheap and Fast Pipeline for Iteratively Cleaning Label Uncertainties (Technical Report)Code0
Quantum Deep Learning: Sampling Neural Nets with a Quantum Annealer0
Just Train Twice: Improving Group Robustness without Training Group InformationCode1
OODformer: Out-Of-Distribution Detection TransformerCode1
Show:102550
← PrevPage 226 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