Few-Shot Remote Sensing Scene Classification (FSRSSC) is an important task, which aims to recognize novel scene classes with few examples. Recently, several studies attempt to address the FSRSSC problem by following few-shot natural image classification methods. These existing methods have made promising progress and achieved superior performance. However, they all overlook two unique characteristics of remote sensing images: (i) object co-occurrence that multiple objects tend to appear together in a scene image and (ii) object spatial correlation that these co-occurrence objects are distributed in the scene image following some spatial structure patterns. Such unique characteristics are very beneficial for FSRSSC, which can effectively alleviate the scarcity issue of labeled remote sensing images since they can provide more refined descriptions for each scene class. To fully exploit these characteristics, we propose a novel scene graph matching-based meta-learning framework for FSRSSC, called SGMNet. In this framework, a scene graph construction module is carefully designed to represent each test remote sensing image or each scene class as a scene graph, where the nodes reflect these co-occurrence objects meanwhile the edges capture the spatial correlations between these co-occurrence objects. Then, a scene graph matching module is further developed to evaluate the similarity score between each test remote sensing image and each scene class. Finally, based on the similarity scores, we perform the scene class prediction via a nearest neighbor classifier. We conduct extensive experiments on UCMerced LandUse, WHU19, AID, and NWPU-RESISC45 datasets. The experimental results show that our method obtains superior performance over the previous state-of-the-art methods.
Underspecification and fairness in machine learning (ML) applications have recently become two prominent issues in the ML community. Acoustic scene classification (ASC) applications have so far remained unaffected by this discussion, but are now becoming increasingly used in real-world systems where fairness and reliability are critical aspects. In this work, we argue for the need of a more holistic evaluation process for ASC models through disaggregated evaluations. This entails taking into account performance differences across several factors, such as city, location, and recording device. Although these factors play a well-understood role in the performance of ASC models, most works report single evaluation metrics taking into account all different strata of a particular dataset. We argue that metrics computed on specific sub-populations of the underlying data contain valuable information about the expected real-world behaviour of proposed systems, and their reporting could improve the transparency and trustability of such systems. We demonstrate the effectiveness of the proposed evaluation process in uncovering underspecification and fairness problems exhibited by several standard ML architectures when trained on two widely-used ASC datasets. Our evaluation shows that all examined architectures exhibit large biases across all factors taken into consideration, and in particular with respect to the recording location. Additionally, different architectures exhibit different biases even though they are trained with the same experimental configurations.
With the emergence of autonomous indoor robots, the computer vision task of indoor scene recognition has gained the spotlight. Indoor scene recognition is a challenging problem in computer vision that relies on local and global features in a scene. This study aims to compare the performance of five machine learning algorithms on the task of indoor scene classification to identify the pros and cons of each classifier. It also provides a comparison of low latency feature extractors versus enormous feature extractors to understand the performance effects. Finally, a simple MnasNet based indoor classification system is proposed, which can achieve 72% accuracy at 23 ms latency.
Acoustic scene classification (ASC) aims to identify the type of scene (environment) in which a given audio signal is recorded. The log-mel feature and convolutional neural network (CNN) have recently become the most popular time-frequency (TF) feature representation and classifier in ASC. An audio signal recorded in a scene may include various sounds overlapping in time and frequency. The previous study suggests that separately considering the long-duration sounds and short-duration sounds in CNN may improve ASC accuracy. This study addresses the problem of the generalization ability of acoustic scene classifiers. In practice, acoustic scene signals' characteristics may be affected by various factors, such as the choice of recording devices and the change of recording locations. When an established ASC system predicts scene classes on audios recorded in unseen scenarios, its accuracy may drop significantly. The long-duration sounds not only contain domain-independent acoustic scene information, but also contain channel information determined by the recording conditions, which is prone to over-fitting. For a more robust ASC system, We propose a robust feature learning (RFL) framework to train the CNN. The RFL framework down-weights CNN learning specifically on long-duration sounds. The proposed method is to train an auxiliary classifier with only long-duration sound information as input. The auxiliary classifier is trained with an auxiliary loss function that assigns less learning weight to poorly classified examples than the standard cross-entropy loss. The experimental results show that the proposed RFL framework can obtain a more robust acoustic scene classifier towards unseen devices and cities.
We present an iVector based Acoustic Scene Classification (ASC) system suited for real life settings where active foreground speech can be present. In the proposed system, each recording is represented by a fixed-length iVector that models the recording's important properties. A regularized Gaussian backend classifier with class-specific covariance models is used to extract the relevant acoustic scene information from these iVectors. To alleviate the large performance degradation when a foreground speaker dominates the captured signal, we investigate the use of the iVector framework on Mel-Frequency Cepstral Coefficients (MFCCs) that are derived from an estimate of the noise power spectral density. This noise-floor can be extracted in a statistical manner for single channel recordings. We show that the use of noise-floor features is complementary to multi-condition training in which foreground speech is added to training signal to reduce the mismatch between training and testing conditions. Experimental results on the DCASE 2016 Task 1 dataset show that the noise-floor based features and multi-condition training realize significant classification accuracy gains of up to more than 25 percentage points (absolute) in the most adverse conditions. These promising results can further facilitate the integration of ASC in resource-constrained devices such as hearables.
Acoustic scene classification (ASC) is one of the most popular problems in the field of machine listening. The objective of this problem is to classify an audio clip into one of the predefined scenes using only the audio data. This problem has considerably progressed over the years in the different editions of DCASE. It usually has several subtasks that allow to tackle this problem with different approaches. The subtask presented in this report corresponds to a ASC problem that is constrained by the complexity of the model as well as having audio recorded from different devices, known as mismatch devices (real and simulated). The work presented in this report follows the research line carried out by the team in previous years. Specifically, a system based on two steps is proposed: a two-dimensional representation of the audio using the Gamamtone filter bank and a convolutional neural network using squeeze-excitation techniques. The presented system outperforms the baseline by about 17 percentage points.
There has been a recent surge of research interest in attacking the problem of social relation inference based on images. Existing works classify social relations mainly by creating complicated graphs of human interactions, or learning the foreground and/or background information of persons and objects, but ignore holistic scene context. The holistic scene refers to the functionality of a place in images, such as dinning room, playground and office. In this paper, by mimicking human understanding on images, we propose an approach of \textbf{PR}actical \textbf{I}nference in \textbf{S}ocial r\textbf{E}lation (PRISE), which concisely learns interactive features of persons and discriminative features of holistic scenes. Technically, we develop a simple and fast relational graph convolutional network to capture interactive features of all persons in one image. To learn the holistic scene feature, we elaborately design a contrastive learning task based on image scene classification. To further boost the performance in social relation inference, we collect and distribute a new large-scale dataset, which consists of about 240 thousand unlabeled images. The extensive experimental results show that our novel learning framework significantly beats the state-of-the-art methods, e.g., PRISE achieves 6.8$\%$ improvement for domain classification in PIPA dataset.
The use of multiple and semantically correlated sources can provide complementary information to each other that may not be evident when working with individual modalities on their own. In this context, multi-modal models can help producing more accurate and robust predictions in machine learning tasks where audio-visual data is available. This paper presents a multi-modal model for automatic scene classification that exploits simultaneously auditory and visual information. The proposed approach makes use of two separate networks which are respectively trained in isolation on audio and visual data, so that each network specializes in a given modality. The visual subnetwork is a pre-trained VGG16 model followed by a bidiretional recurrent layer, while the residual audio subnetwork is based on stacked squeeze-excitation convolutional blocks trained from scratch. After training each subnetwork, the fusion of information from the audio and visual streams is performed at two different stages. The early fusion stage combines features resulting from the last convolutional block of the respective subnetworks at different time steps to feed a bidirectional recurrent structure. The late fusion stage combines the output of the early fusion stage with the independent predictions provided by the two subnetworks, resulting in the final prediction. We evaluate the method using the recently published TAU Audio-Visual Urban Scenes 2021, which contains synchronized audio and video recordings from 12 European cities in 10 different scene classes. The proposed model has been shown to provide an excellent trade-off between prediction performance (86.5%) and system complexity (15M parameters) in the evaluation results of the DCASE 2021 Challenge.
Convolutional Neural Networks (CNNs) have been dominating classification tasks in various domains, such as machine vision, machine listening, and natural language processing. In machine listening, while generally exhibiting very good generalization capabilities, CNNs are sensitive to the specific audio recording device used, which has been recognized as a substantial problem in the acoustic scene classification (DCASE) community. In this study, we investigate the relationship between over-parameterization of acoustic scene classification models, and their resulting generalization abilities. Specifically, we test scaling CNNs in width and depth, under different conditions. Our results indicate that increasing width improves generalization to unseen devices, even without an increase in the number of parameters.
The proliferation of remote sensing satellites has resulted in a massive amount of remote sensing images. However, due to human and material resource constraints, the vast majority of remote sensing images remain unlabeled. As a result, it cannot be applied to currently available deep learning methods. To fully utilize the remaining unlabeled images, we propose a Geographical Knowledge-driven Representation learning method for remote sensing images (GeoKR), improving network performance and reduce the demand for annotated data. The global land cover products and geographical location associated with each remote sensing image are regarded as geographical knowledge to provide supervision for representation learning and network pre-training. An efficient pre-training framework is proposed to eliminate the supervision noises caused by imaging times and resolutions difference between remote sensing images and geographical knowledge. A large scale pre-training dataset Levir-KR is proposed to support network pre-training. It contains 1,431,950 remote sensing images from Gaofen series satellites with various resolutions. Experimental results demonstrate that our proposed method outperforms ImageNet pre-training and self-supervised representation learning methods and significantly reduces the burden of data annotation on downstream tasks such as scene classification, semantic segmentation, object detection, and cloud / snow detection. It demonstrates that our proposed method can be used as a novel paradigm for pre-training neural networks. Codes will be available on https://github.com/flyakon/Geographical-Knowledge-driven-Representaion-Learning.
We propose a novel neural model compression strategy combining data augmentation, knowledge transfer, pruning, and quantization for device-robust acoustic scene classification (ASC). Specifically, we tackle the ASC task in a low-resource environment leveraging a recently proposed advanced neural network pruning mechanism, namely Lottery Ticket Hypothesis (LTH), to find a sub-network neural model associated with a small amount non-zero model parameters. The effectiveness of LTH for low-complexity acoustic modeling is assessed by investigating various data augmentation and compression schemes, and we report an efficient joint framework for low-complexity multi-device ASC, called \emph{Acoustic Lottery}. Acoustic Lottery could compress an ASC model up to $1/10^{4}$ and attain a superior performance (validation accuracy of 79.4% and Log loss of 0.64) compared to its not compressed seed model. All results reported in this work are based on a joint effort of four groups, namely GT-USTC-UKE-Tencent, aiming to address the "Low-Complexity Acoustic Scene Classification (ASC) with Multiple Devices" in the DCASE 2021 Challenge Task 1a.
To assist human drivers and autonomous vehicles in assessing crash risks, driving scene analysis using dash cameras on vehicles and deep learning algorithms is of paramount importance. Although these technologies are increasingly available, driving scene analysis for this purpose still remains a challenge. This is mainly due to the lack of annotated large image datasets for analyzing crash risk indicators and crash likelihood, and the lack of an effective method to extract lots of required information from complex driving scenes. To fill the gap, this paper develops a scene analysis system. The Multi-Net of the system includes two multi-task neural networks that perform scene classification to provide four labels for each scene. The DeepLab v3 and YOLO v3 are combined by the system to detect and locate risky pedestrians and the nearest vehicles. All identified information can provide the situational awareness to autonomous vehicles or human drivers for identifying crash risks from the surrounding traffic. To address the scarcity of annotated image datasets for studying traffic crashes, two completely new datasets have been developed by this paper and made available to the public, which were proved to be effective in training the proposed deep neural networks. The paper further evaluates the performance of the Multi-Net and the efficiency of the developed system. Comprehensive scene analysis is further illustrated with representative examples. Results demonstrate the effectiveness of the developed system and datasets for driving scene analysis, and their supportiveness for crash risk assessment and crash prevention.
In this paper, we propose a transfer-learning based model construction technique for the aerial scene classification problem. The core of our technique is a layer selection strategy, named ReLU-Based Feature Fusion (RBFF), that extracts feature maps from a pretrained CNN-based single-object image classification model, namely MobileNetV2, and constructs a model for the aerial scene classification task. RBFF stacks features extracted from the batch normalization layer of a few selected blocks of MobileNetV2, where the candidate blocks are selected based on the characteristics of the ReLU activation layers present in those blocks. The feature vector is then compressed into a low-dimensional feature space using dimension reduction algorithms on which we train a low-cost SVM classifier for the classification of the aerial images. We validate our choice of selected features based on the significance of the extracted features with respect to our classification pipeline. RBFF remarkably does not involve any training of the base CNN model except for a few parameters for the classifier, which makes the technique very cost-effective for practical deployments. The constructed model despite being lightweight outperforms several recently proposed models in terms of accuracy for a number of aerial scene datasets.
This paper presents the details of Task 1A Acoustic Scene Classification in the DCASE 2021 Challenge. The task targeted development of low-complexity solutions with good generalization properties. The provided baseline system is based on a CNN architecture and post-training quantization of parameters. The system is trained using all the available training data, without any specific technique for handling device mismatch, and obtains an overall accuracy of 47.7%, with a log loss of 1.473. The task received 99 submissions from 30 teams, and most of the submitted systems outperformed the baseline. The most used techniques among the submissions were residual networks and weight quantization, with the top systems reaching over 70% accuracy, and log loss under 0.8. The acoustic scene classification task remained a popular task in the challenge, despite the increasing difficulty of the setup.
This paper presents the details of the Audio-Visual Scene Classification task in the DCASE 2021 Challenge (Task 1 Subtask B). The task is concerned with classification using audio and video modalities, using a dataset of synchronized recordings. This task has attracted 43 submissions from 13 different teams around the world. Among all submissions, more than half of the submitted systems have better performance than the baseline. The common techniques among the top systems are the usage of large pretrained models such as ResNet or EfficientNet which are trained for the task-specific problem. Fine-tuning, transfer learning, and data augmentation techniques are also employed to boost the performance. More importantly, multi-modal methods using both audio and video are employed by all the top 5 teams. The best system among all achieved a logloss of 0.195 and accuracy of 93.8%, compared to the baseline system with logloss of 0.662 and accuracy of 77.1%.
In this paper, we study the performance of variants of well-known Convolutional Neural Network (CNN) architectures on different audio tasks. We show that tuning the Receptive Field (RF) of CNNs is crucial to their generalization. An insufficient RF limits the CNN's ability to fit the training data. In contrast, CNNs with an excessive RF tend to over-fit the training data and fail to generalize to unseen testing data. As state-of-the-art CNN architectures-in computer vision and other domains-tend to go deeper in terms of number of layers, their RF size increases and therefore they degrade in performance in several audio classification and tagging tasks. We study well-known CNN architectures and how their building blocks affect their receptive field. We propose several systematic approaches to control the RF of CNNs and systematically test the resulting architectures on different audio classification and tagging tasks and datasets. The experiments show that regularizing the RF of CNNs using our proposed approaches can drastically improve the generalization of models, out-performing complex architectures and pre-trained models on larger datasets. The proposed CNNs achieve state-of-the-art results in multiple tasks, from acoustic scene classification to emotion and theme detection in music to instrument recognition, as demonstrated by top ranks in several pertinent challenges (DCASE, MediaEval).
Machine learning algorithms, when trained on audio recordings from a limited set of devices, may not generalize well to samples recorded using other devices with different frequency responses. In this work, a relatively straightforward method is introduced to address this problem. Two variants of the approach are presented. First requires aligned examples from multiple devices, the second approach alleviates this requirement. This method works for both time and frequency domain representations of audio recordings. Further, a relation to standardization and Cepstral Mean Subtraction is analysed. The proposed approach becomes effective even when very few examples are provided. This method was developed during the Detection and Classification of Acoustic Scenes and Events (DCASE) 2019 challenge and won the 1st place in the scenario with mis-matched recording devices with the accuracy of 75%. Source code for the experiments can be found online.
To realize high-accuracy classification of high spatial resolution (HSR) images, this letter proposes a new multi-feature fusion-based scene classification framework (MF2SCF) by fusing local, global, and color features of HSR images. Specifically, we first extract the local features with the help of image slicing and densely connected convolutional networks (DenseNet), where the outputs of dense blocks in the fine-tuned DenseNet-121 model are jointly averaged and concatenated to describe local features. Second, from the perspective of complex networks (CN), we model a HSR image as an undirected graph based on pixel distance, intensity, and gradient, and obtain a gray-scale image (GSI), a gradient of image (GoI), and three CN-based feature images to delineate global features. To make the global feature descriptor resist to the impact of rotation and illumination, we apply uniform local binary patterns (LBP) on GSI, GoI, and feature images, respectively, and generate the final global feature representation by concatenating spatial histograms. Third, the color features are determined based on the normalized HSV histogram, where HSV stands for hue, saturation, and value, respectively. Finally, three feature vectors are jointly concatenated for scene classification. Experiment results show that MF2SCF significantly improves the classification accuracy compared with state-of-the-art LBP-based methods and deep learning-based methods.
This paper presents the details of Task 1: Acoustic Scene Classification in the DCASE 2020 Challenge. The task consists of two subtasks: classification of data from multiple devices, requiring good generalization properties, and classification using low-complexity solutions. Here we describe the datasets and baseline systems. After the challenge submission deadline, challenge results and analysis of the submissions will be added.
Camera scene detection is among the most popular computer vision problem on smartphones. While many custom solutions were developed for this task by phone vendors, none of the designed models were available publicly up until now. To address this problem, we introduce the first Mobile AI challenge, where the target is to develop quantized deep learning-based camera scene classification solutions that can demonstrate a real-time performance on smartphones and IoT platforms. For this, the participants were provided with a large-scale CamSDD dataset consisting of more than 11K images belonging to the 30 most important scene categories. The runtime of all models was evaluated on the popular Apple Bionic A11 platform that can be found in many iOS devices. The proposed solutions are fully compatible with all major mobile AI accelerators and can demonstrate more than 100-200 FPS on the majority of recent smartphone platforms while achieving a top-3 accuracy of more than 98%. A detailed description of all models developed in the challenge is provided in this paper.