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 34113420 of 10420 papers

TitleStatusHype
Img2Tab: Automatic Class Relevant Concept Discovery from StyleGAN Features for Explainable Image Classification0
Modeling Uncertain Feature Representation for Domain GeneralizationCode1
First Three Years of the International Verification of Neural Networks Competition (VNN-COMP)0
Gated Self-supervised Learning For Improving Supervised Learning0
CLIP the Gap: A Single Domain Generalization Approach for Object DetectionCode1
A Scalable Technique for Weak-Supervised Learning with Domain Constraints0
Color-NeuraCrypt: Privacy-Preserving Color-Image Classification Using Extended Random Neural Networks0
1st Place Solution for ECCV 2022 OOD-CV Challenge Image Classification TrackCode0
Online Class-Incremental Learning For Real-World Food Image ClassificationCode0
A Stochastic Proximal Polyak Step SizeCode0
Show:102550
← PrevPage 342 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
10RevCol-HTop 1 Accuracy90Unverified