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 33513360 of 10420 papers

TitleStatusHype
On Suppressing Range of Adaptive Stepsizes of Adam to Improve Generalisation Performance0
mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and VideoCode4
Structured mutation inspired by evolutionary theory enriches population performance and diversity0
Deep Dependency Networks for Multi-Label Classification0
Image-Based Vehicle Classification by Synergizing Features from Supervised and Self-Supervised Learning Paradigms0
Weight Prediction Boosts the Convergence of AdamW0
NASiam: Efficient Representation Learning using Neural Architecture Search for Siamese NetworksCode0
Training with Mixed-Precision Floating-Point Assignments0
Does Deep Active Learning Work in the Wild?0
NP-Match: Towards a New Probabilistic Model for Semi-Supervised LearningCode1
Show:102550
← PrevPage 336 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