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 301310 of 453 papers

TitleStatusHype
Cross-task pre-training for on-device acoustic scene classification0
Acoustic Scene Classification Based on a Large-margin Factorized CNN0
Residual Attention Graph Convolutional Network for Geometric 3D Scene Classification0
Acoustic scene analysis with multi-head attention networksCode0
Receptive-field-regularized CNN variants for acoustic scene classificationCode1
Semantic-Aware Scene RecognitionCode0
Exploiting Parallel Audio Recordings to Enforce Device Invariance in CNN-based Acoustic Scene ClassificationCode0
Online Sensor Hallucination via Knowledge Distillation for Multimodal Image Classification0
Multiple instance dense connected convolution neural network for aerial image scene classification0
Scene Classification in Indoor Environments for Robots using Context Based Word Embeddings0
Show:102550
← PrevPage 31 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