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 15811590 of 10420 papers

TitleStatusHype
Gradient Matching for Domain GeneralizationCode1
Differentiable Model Compression via Pseudo Quantization NoiseCode1
Contrastive Learning Improves Model Robustness Under Label NoiseCode1
Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?Code1
"BNN - BN = ?": Training Binary Neural Networks without Batch NormalizationCode1
AsymmNet: Towards ultralight convolution neural networks using asymmetrical bottlenecksCode1
A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data AugmentationCode1
Self-Supervised Learning of Remote Sensing Scene Representations Using Contrastive Multiview CodingCode1
ViT-V-Net: Vision Transformer for Unsupervised Volumetric Medical Image RegistrationCode1
Fast Hierarchical Games for Image ExplanationsCode1
Show:102550
← PrevPage 159 of 1042Next →

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
5DaViT-HTop 1 Accuracy90.2Unverified
6Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2Unverified
7SwinV2-GTop 1 Accuracy90.17Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05Unverified
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90Unverified