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 1–10 of 453 papers

TitleStatusHype
Towards Scalable and Generalizable Earth Observation Data Mining via Foundation Model Composition—0
A Challenge to Build Neuro-Symbolic Video AgentsCode0
EarthSynth: Generating Informative Earth Observation with Diffusion Models—0
Energy efficiency analysis of Spiking Neural Networks for space applications—0
Minimizing Risk Through Minimizing Model-Data Interaction: A Protocol For Relying on Proxy Tasks When Designing Child Sexual Abuse Imagery Detection Models—0
Low-Complexity Acoustic Scene Classification with Device Information in the DCASE 2025 ChallengeCode0
FrogDogNet: Fourier frequency Retained visual prompt Output Guidance for Domain Generalization of CLIP in Remote SensingCode0
FlexiMo: A Flexible Remote Sensing Foundation Model—0
Open-Vocabulary Semantic Segmentation with Uncertainty Alignment for Robotic Scene Understanding in Indoor Building Environments—0
Vanishing Depth: A Depth Adapter with Positional Depth Encoding for Generalized Image EncodersCode0
Show:102550
← PrevPage 1 of 46Next →

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