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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 251–260 of 453 papers

TitleStatusHype
Semantic Fisher Scores for Task Transfer: Using Objects to Classify Scenes—0
Sensing Urban Land-Use Patterns By Integrating Google Tensorflow And Scene-Classification Models—0
SGMNet: Scene Graph Matching Network for Few-Shot Remote Sensing Scene Classification—0
Shape Distributions of Nonlinear Dynamical Systems for Video-based Inference—0
Short-Term Memory Convolutions—0
SOAT: A Scene- and Object-Aware Transformer for Vision-and-Language Navigation—0
Solving Visual Madlibs with Multiple Cues—0
Sparse Output Coding for Large-Scale Visual Recognition—0
Spatio-Temporal Attention Pooling for Audio Scene Classification—0
SpecAugment++: A Hidden Space Data Augmentation Method for Acoustic Scene Classification—0
Show:102550
← PrevPage 26 of 46Next →
All datasetsUC Merced Land Use DatasetPlaces365-Standard

Benchmark Results

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