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 18611870 of 10420 papers

TitleStatusHype
Generative Classifiers as a Basis for Trustworthy Image ClassificationCode1
Dynamic Defense Against Byzantine Poisoning Attacks in Federated LearningCode1
A General Framework For Detecting Anomalous Inputs to DNN ClassifiersCode1
Split Computing for Complex Object Detectors: Challenges and Preliminary ResultsCode1
The MAMe Dataset: On the relevance of High Resolution and Variable Shape image propertiesCode1
MaxDropout: Deep Neural Network Regularization Based on Maximum Output ValuesCode1
HATNet: An End-to-End Holistic Attention Network for Diagnosis of Breast Biopsy ImagesCode1
Deep Network Ensemble Learning applied to Image Classification using CNN TreesCode1
DEAL: Deep Evidential Active Learning for Image ClassificationCode1
CyCNN: A Rotation Invariant CNN using Polar Mapping and Cylindrical Convolution LayersCode1
Show:102550
← PrevPage 187 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