HexaConv improves CNN performance by using hexagonal filters and group convolutions.
problem Improving CNN performance by exploiting more symmetries.
method Implementing planar and group convolutions over hexagonal lattices.
result HexaConv outperforms conventional CNNs on aerial scene classification.
Deep learning aids UAVs in identifying disasters with high accuracy.
problem Monitoring disasters for effective mitigation.
method Deep learning applied to aerial photos from UAVs.
result 91% accuracy in disaster identification from 544 images.
This paper classifies typhoon damage features using aerial photography.
problem Typhoon damages and slow recovery times.
method Aerial photography for classification of eight classes including land covers and disaster areas.
result Visualize and explain typhoon disaster features using convolutional activation maps.
Aerial robot estimates human pose and path using dynamic classifier selection.
problem Estimating human pose and trajectory from aerial video.
method Dynamic classifier selection architecture; perspective correction; HOG and CNN features; 64 pose-viewpoint classes.
result Dynamic classifier selection improves efficiency and accuracy.
Enhances sound texture in CNN for better acoustic scene classification.
problem Limited understanding of how CNNs perceive audio scenes.
method Used Class Activation Mapping (CAM) to analyze log-Mel features and proposed edge enhancement using DoG and Sobel operators.
result Edge-enhanced log-Mel features improve CNN performance in acoustic scene classification.
Improved acoustic scene classification with factorized CNN.
problem Acoustic scene classification in varying environments.
method Large-margin factorized CNN with triplet loss.
result Improved performance and better generalization on unseen data.
Deep learning classifies land use from high-resolution aerial imagery.
problem Variations in land features in aerial imagery due to sensor settings and context.
method Used deep convolutional neural networks to classify land use from VHR orthophoto mosaics.
result Deep learning can accurately classify land use from high-resolution visible band multispectral imagery.
Paper proposes Q-learning for efficient aerial BS placement to improve fairness in mobile networks.
problem Optimal placement of aerial base stations to enhance fairness in a dynamic user mobility environment.
method Reinforcement learning approach to solve the NP-hard problem of 3D placement.
result Simulation results show increased fairness among users with a reasonable computing time and solution close to optimal.
This paper evaluates conformal prediction for aerial image classification in challenging environments.
problem Challenging aerial image classification in data-scarce, unconstrained environments.
method Conformal prediction applied to pretrained models (MobileNet, DenseNet, ResNet) with limited labeled data.
result Conformal prediction can provide valuable uncertainty estimates even with small labeled samples.
Paper proposes a voting method to improve acoustic scene classification.
problem Improving acoustic scene classification accuracy.
method Punishment voting algorithm based on super categories construction.
result Punishment voting significantly improves classification performance.
MRCNet tackles crowd counting and density mapping in aerial imagery.
problem Accurate crowd counting and density estimation in aerial imagery.
method MRCNet is a novel encoder-decoder CNN that combines VGG-16 with FPN-inspired lateral connections.
result MRCNet outperforms state-of-the-art methods in aerial and CCTV-based crowd counting.
Review of acoustic scene classification methods in a competition.
problem Categorizing audio sequences into classes based on spectral content.
method Competition involving students and external participants, ablation study, neural network baseline comparison.
result Improved classification over neural network baseline.
A simple fusion of deep and shallow learning improves acoustic scene classification.
problem Improving acoustic scene classification accuracy.
method Combining a deep learning approach and a feature engineering approach using a late fusion strategy.
result The fused system achieves 72.8% classification accuracy, outperforming individual methods.
DALES offers a large annotated aerial LiDAR dataset for 3D deep learning.
problem Lack of large-scale annotated aerial LiDAR datasets for deep learning.
method Collection and annotation of over half a billion hand-labeled points from an ALS scanner.
result DALES is the most extensive publicly available ALS data set with improved resolution and coverage.
A new neural network learns from acoustic scenes by suppressing irrelevant patterns.
problem Acoustic scenes are rich and redundant, making classification challenging.
method Spatio-temporal attention pooling layer coupled with a convolutional recurrent neural network.
result The method outperforms a strong convolutional neural network baseline and sets new state-of-the-art performance.
CNNs improve generalization to unseen audio devices with increased width, not depth.
problem CNNs are sensitive to specific audio recording devices in acoustic scene classification.
method Investigated the relationship between over-parameterization and generalization in CNNs for audio classification.
result Increasing width improves generalization to unseen devices without increasing the number of parameters.
A multi-head attention network improves ASC by recognizing overlapping sound patterns.
problem Challenging ASC due to overlapping sound patterns and complex event mixtures.
method Proposes a multi-head attention network to model complex temporal input structures.
result Achieved competitive performance on DCASE 2018 Task 5 dataset.
Bayesian fusion improves radar target recognition for UAVs.
problem Improving radar target recognition for UAVs using multistatic radar configurations.
method Proposes a fully Bayesian RATR framework using Optimal Bayesian Fusion (OBF) to aggregate classification probability vectors from multiple radars.
result Empirical results show that the OBF method significantly enhances classification accuracy compared to other fusion methods and single radar configurations.
Study improves CNNs for audio scene classification by restricting receptive fields and adding frequency awareness.
problem Improving CNNs for robust acoustic scene classification.
method Investigated different receptive field configurations for various CNN architectures and introduced Frequency Aware CNNs.
result Several well-performing submissions to DCASE 2019 Challenge were achieved.
Despite enormous progress in object detection and classification, the problem of incorporating expected contextual relationships among object instances into modern recognition systems remains a key challenge. In this work we propose Information Pursuit, a Bayesian framework for scene parsing that combines prior models …
Paper proposes a method to improve building extraction from aerial images by adapting CNN models.
problem Limited generalization of CNN-based segmentation models for unseen images.
method Combines domain transfer and adversarial attack concepts to adapt input images to target images.
result Improves overall IoU and outperforms other methods in cross-dataset experiments.
Proposes a method to quantify uncertainty in deterministic image classifiers.
problem Uncertainty in deterministic image classifiers.
method Introduces Wellington Posterior for inductive transfer from scenes.
result Validates Wellington Posterior using various methods.
Paper proposes efficient UAV placement for aerial base stations.
problem Efficient placement of UAVs as aerial base stations to serve varying traffic demand.
method Modeling UAV deployment as a non-cooperative game and using a learning-based algorithm to update UAV locations.
result Significant performance gains up to 52% and 74% in terms of throughput and dropped users compared to an optimized baseline algorithm.
New method uses overcomplete frames for better acoustic scene analysis.
problem Improving acoustic scene analysis in real-world applications.
method Risk minimization-based overcomplete frame thresholding.
result Validated on bird activity detection task using wavelets.
A lightweight network and NAS method improve ASC tasks.
problem Heavy computational burden in acoustic scene classification.
method Inspired by MobileNetV2, unidirectional convolutions; dynamic NAS with evolutionary algorithm.
result 90.3% F1-score on DCASE2018 task 5, 25% fewer FLOPs.
Method generates uncertainty measures for street scene segmentation.
problem Reliability and uncertainty measures in semantic segmentation of street scenes.
method Nested crops, neural network segmentation, post-processing, uncertainty heat maps.
result Significant improvements in classification and regression performance.
Study uses aerial or satellite imagery to improve land price prediction in Thailand.
problem Limited accuracy of traditional land price prediction methods.
method Proposes a similarity-based asset valuation model using Siamese-inspired Neural Network and ensembles deep learning and tree-based models.
result Achieves an AUC of approximately 0.81, outperforming traditional methods.
End-to-end DA method for domain-invariant CNNs using parallel audio recordings.
problem Distribution mismatches between training and application data in machine listening.
method Enforcing equal hidden layer representations for domain-parallel samples.
result Learn domain-invariant classifiers without requiring classification labels.
Transformer model estimates keywords for better audio captioning.
problem Indeterminacy in word selection for audio events/scenes.
method Transformer-based model with keyword estimation.
result Achieved state-of-the-art performance in AAC.
Proposes LML layer for multi-label predictions with k labels.
problem Efficient multi-label prediction with limited labels.
method Probabilistic multi-label modeling, efficient forward and backward passes.
result Improves top-k recall and accuracy in multi-label tasks.
A neural scene representation framework enforcing 3D transformations.
problem Learning 3D scene representations from images without 3D supervision.
method Introducing a loss enforcing equivariance of the scene representation with 3D transformations.
result Real-time neural rendering with comparable results to models requiring minutes for inference.
Improved CNN model accuracy and generalizability through data pre-processing.
problem Enhancing accuracy and generalizability of CNN-based LULC classification.
method Trials of different data preparation methods, including patch selection, size, and augmentations.
result Combining multiple grids and rotations of patches improved model accuracy and generalizability.
The paper generates a comprehensive training dataset for land cover classification.
problem Insufficient training datasets for land cover classification.
method Public Sentinel-2 data at 10m resolution matched with accurate labels, filtered and classified by Random Forests.
result Over 80% model accuracy for various locations.
Enhances ASC using time- and frequency-liked CNNs and bilinear pooling.
problem Improving acoustic scene classification accuracy.
method Harmonic and percussive source separation, two-stream CNN architecture, bilinear pooling.
result Improved accuracy on DCASE 2019 sub task 1a dataset.
This paper analyzes sound event detection in synthetic office audio, comparing different systems.
problem Comparing sound event detection systems in synthetic office audio.
method Analysis of systems submitted to DCASE 2016 task, using synthetic office sounds.
result Statistical analysis of results, highlighting system performance under controlled conditions.
GENESIS generates and samples 3D scenes by capturing object interactions.
problem Lack of models that explicitly capture object interactions in scene generation.
method Object-centric latent variables, spatial GMM, amortized inference, autoregressive prior.
result First object-centric generative model of 3D visual scenes.
Efficient model for foggy scene understanding in vehicles.
problem Challenging scene understanding and segmentation under foggy conditions.
method Domain adaptation and illumination-invariant image transformation.
result Outperforms state-of-the-art models in foggy scene understanding.
Improved deep CNNs for ASC by optimizing receptive field size.
problem Deep CNNs perform poorly in ASC compared to simpler models.
method Analyzed and adapted the receptive field of ResNet and DenseNet.
result State-of-the-art performance achieved with optimized receptive field.
Scene text magnifier enhances readability for visually impaired.
problem Helps visually impaired read natural scene text.
method Four CNN-based networks: character erasing, extraction, magnify, synthesis.
result Effective text magnification without background alteration.
New model separates objects in scenes, enabling novel arrangements and depth.
problem Lack of modular, compositional scene modeling in generative models.
method Ensemble of generative models (experts) compete for explaining different parts of a scene.
result Model generates scenes with novel object arrangement and depth ordering.
Unified approach for learning with weak labels across various tasks.
problem Learning with noisy or incomplete labels in diverse machine learning settings.
method Implicit posterior models for joint label inference.
result Unified training objective for various machine learning tasks.
ROOTS learns to represent and render 3D scenes with object-centric models.
problem Learning to represent and render 3D scenes with object-centric compositionality.
method Probabilistic generative model for learning object representations and scene rendering from partial observations.
result The model can infer 3D object representations and render scenes from arbitrary viewpoints.
MONet learns to decompose scenes into meaningful components without supervision.
problem Learning meaningful scene decompositions without labeled data.
method MONet combines a VAE and recurrent attention network to learn decompositions of 3D scenes.
result MONet can learn to represent 3D scenes into meaningful components like objects and background.
SPACE models complex scenes by decomposing objects and backgrounds.
problem Scalability and unsupervised object-oriented scene representation learning.
method Generative latent variable model combining spatial-attention and scene-mixture approaches.
result SPACE achieves factorized object representations and decomposes complex scenes.
NeRF-VAE generates 3D scenes with geometric structure from few images.
problem Generating 3D scenes from few images with geometric consistency.
method Combines NeRF and VAE, incorporating shared geometric structure.
result NeRF-VAE can infer and render geometrically-consistent scenes from unseen environments.
Study uses SAR data to map defoliation and regrowth in tundra-forest areas.
problem Mapping defoliation and regrowth in tundra-forest areas using SAR data.
method Novel guided nonlocal means speckle filtering of polarimetric covariance matrix.
result Over 99.7% classification accuracy in defoliation and regrowth mapping.
Topic modeling based on latent Dirichlet allocation (LDA) has been a framework of choice to perform scene recognition and annotation. Recently, a new type of topic model called the Document Neural Autoregressive Distribution Estimator (DocNADE) was proposed and demonstrated state-of-the-art performance for document mod…
A new method for estimating joint value functions in multi-scene reinforcement learning.
problem High variance in samples for policy gradient computations in multi-scene environments.
method Sparse attention mechanism over multiple value function hypotheses to approximate the true joint value function.
result Significant improvements in reward scores and enhanced navigation efficiency across OpenAI ProcGen environments.