SOTAVerified

Scene Classification

Scene Classification is a task in which scenes from photographs are categorically classified. Unlike object classification, which focuses on classifying prominent objects in the foreground, Scene Classification uses the layout of objects within the scene, in addition to the ambient context, for classification.

Source: Scene classification with Convolutional Neural Networks

Papers

Showing 121130 of 453 papers

TitleStatusHype
Generalized Scene Classification from Small-Scale Datasets with Multi-Task LearningCode0
Efficient Multi-Resolution Fusion for Remote Sensing Data with Label UncertaintyCode0
All grains, one scheme (AGOS): Learning multigrain instance representation for aerial scene classificationCode0
Domain Information Control at Inference Time for Acoustic Scene ClassificationCode0
AudioLog: LLMs-Powered Long Audio Logging with Hybrid Token-Semantic Contrastive LearningCode0
Acoustic scene analysis with multi-head attention networksCode0
Deliberative Explanations: visualizing network insecuritiesCode0
Efficient Similarity-based Passive Filter Pruning for Compressing CNNsCode0
DeepCorrect: Correcting DNN models against Image DistortionsCode0
A Continual Development Methodology for Large-scale Multitask Dynamic ML SystemsCode0
Show:102550
← PrevPage 13 of 46Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1µ2Net+ (ViT-L/16)Accuracy (%)100Unverified
2AGOSAccuracy (%)99.88Unverified
3LSE-NetAccuracy (%)99.78Unverified
4ResNet50Accuracy (%)99.61Unverified
5MSMatchAccuracy (%)98.33Unverified
6MIDC-NetAccuracy (%)97.4Unverified
#ModelMetricClaimedVerifiedStatus
1iSQRT-COV-Net (ResNet-50)Top 1 Error43.68Unverified
2WaveMixTop 1 Error43.55Unverified