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 601610 of 10420 papers

TitleStatusHype
MCUFormer: Deploying Vision Transformers on Microcontrollers with Limited MemoryCode1
Vision-Language Pseudo-Labels for Single-Positive Multi-Label LearningCode1
Interpretable Medical Image Classification using Prototype Learning and Privileged InformationCode1
SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and GenerationCode1
Multi‑camera trajectory matching based on hierarchical clustering and constraintsCode1
Image Clustering with External GuidanceCode1
Real-Fake: Effective Training Data Synthesis Through Distribution MatchingCode1
RefConv: Re-parameterized Refocusing Convolution for Powerful ConvNetsCode1
PaLI-3 Vision Language Models: Smaller, Faster, StrongerCode1
AutoVP: An Automated Visual Prompting Framework and BenchmarkCode1
Show:102550
← PrevPage 61 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
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