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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 11–20 of 453 papers

Title	Date	Tasks	Status	Hype
RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing	Mar 13, 2025	Computational EfficiencyMamba	CodeCode Available	2
TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data	Oct 8, 2024	Change DetectionEarth Observation	CodeCode Available	2
LWGANet: A Lightweight Group Attention Backbone for Remote Sensing Visual Tasks	Jan 17, 2025	Change DetectionImage Classification	CodeCode Available	2
SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing	Dec 20, 2023	AttributeCross-Modal Retrieval	CodeCode Available	2
DCASENET: A joint pre-trained deep neural network for detecting and classifying acoustic scenes and events	Sep 21, 2020	Acoustic Scene ClassificationAudio Tagging	CodeCode Available	1
Convolutional Neural Networks Based Remote Sensing Scene Classification under Clear and Cloudy Environments	Dec 30, 2021	ClassificationScene Classification	CodeCode Available	1
Debiased Self-Training for Semi-Supervised Learning	Feb 15, 2022	Object RecognitionScene Classification	CodeCode Available	1
CMID: A Unified Self-Supervised Learning Framework for Remote Sensing Image Understanding	Apr 19, 2023	Change DetectionContrastive Learning	CodeCode Available	1
CITISEN: A Deep Learning-Based Speech Signal-Processing Mobile Application	Aug 21, 2020	Acoustic Scene ClassificationData Augmentation	CodeCode Available	1
Consecutive Pretraining: A Knowledge Transfer Learning Strategy with Relevant Unlabeled Data for Remote Sensing Domain	Jul 8, 2022	Land Cover Classificationobject-detection	CodeCode Available	1

Show:10 25 50

← PrevPage 2 of 46Next →

All datasets UC Merced Land Use Dataset Places365-Standard

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	µ2Net+ (ViT-L/16)	Accuracy (%)	100	—	Unverified
2	AGOS	Accuracy (%)	99.88	—	Unverified
3	LSE-Net	Accuracy (%)	99.78	—	Unverified
4	ResNet50	Accuracy (%)	99.61	—	Unverified
5	MSMatch	Accuracy (%)	98.33	—	Unverified
6	MIDC-Net	Accuracy (%)	97.4	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	iSQRT-COV-Net (ResNet-50)	Top 1 Error	43.68	—	Unverified
2	WaveMix	Top 1 Error	43.55	—	Unverified