Aerial scene classification remains challenging as: 1) the size of key objects in determining the scene scheme varies greatly; 2) many objects irrelevant to the scene scheme are often flooded in the image. Hence, how to effectively perceive the region of interests (RoIs) from a variety of sizes and build more discriminative representation from such complicated object distribution is vital to understand an aerial scene. In this paper, we propose a novel all grains, one scheme (AGOS) framework to tackle these challenges. To the best of our knowledge, it is the first work to extend the classic multiple instance learning into multi-grain formulation. Specially, it consists of a multi-grain perception module (MGP), a multi-branch multi-instance representation module (MBMIR) and a self-aligned semantic fusion (SSF) module. Firstly, our MGP preserves the differential dilated convolutional features from the backbone, which magnifies the discriminative information from multi-grains. Then, our MBMIR highlights the key instances in the multi-grain representation under the MIL formulation. Finally, our SSF allows our framework to learn the same scene scheme from multi-grain instance representations and fuses them, so that the entire framework is optimized as a whole. Notably, our AGOS is flexible and can be easily adapted to existing CNNs in a plug-and-play manner. Extensive experiments on UCM, AID and NWPU benchmarks demonstrate that our AGOS achieves a comparable performance against the state-of-the-art methods.
Do we on the right way for remote sensing image understanding (RSIU) by training models via supervised data-dependent and task-dependent way, instead of human vision in a label-free and task-independent way? We argue that a more desirable RSIU model should be trained with intrinsic structure from data rather that extrinsic human labels to realize generalizability across a wide range of RSIU tasks. According to this hypothesis, we proposed \textbf{T}he \textbf{O}riginal \textbf{V}ision model (TOV) in remote sensing filed. Trained by massive unlabeled optical data along a human-like self-supervised learning (SSL) path that is from general knowledge to specialized knowledge, TOV model can be easily adapted to various RSIU tasks, including scene classification, object detection, and semantic segmentation, and outperforms dominant ImageNet supervised pretrained method as well as two recently proposed SSL pretrained methods on majority of 12 publicly available benchmarks. Moreover, we analyze the influences of two key factors on the performance of building TOV model for RSIU, including the influence of using different data sampling methods and the selection of learning paths during self-supervised optimization. We believe that a general model which is trained by a label-free and task-independent way may be the next paradigm for RSIU and hope the insights distilled from this study can help to foster the development of an original vision model for RSIU.
We present a method to develop low-complexity convolutional neural networks (CNNs) for acoustic scene classification (ASC). The large size and high computational complexity of typical CNNs is a bottleneck for their deployment on resource-constrained devices. We propose a passive filter pruning framework, where a few convolutional filters from the CNNs are eliminated to yield compressed CNNs. Our hypothesis is that similar filters produce similar responses and give redundant information allowing such filters to be eliminated from the network. To identify similar filters, a cosine distance based greedy algorithm is proposed. A fine-tuning process is then performed to regain much of the performance lost due to filter elimination. To perform efficient fine-tuning, we analyze how the performance varies as the number of fine-tuning training examples changes. An experimental evaluation of the proposed framework is performed on the publicly available DCASE 2021 Task 1A baseline network trained for ASC. The proposed method is simple, reduces computations per inference by 27%, with 25% fewer parameters, with less than 1% drop in accuracy.
Deep neural networks achieve remarkable performances on a wide range of tasks with the aid of large-scale labeled datasets. Yet these datasets are time-consuming and labor-exhaustive to obtain on realistic tasks. To mitigate the requirement for labeled data, self-training is widely used in semi-supervised learning by iteratively assigning pseudo labels to unlabeled samples. Despite its popularity, self-training is well-believed to be unreliable and often leads to training instability. Our experimental studies further reveal that the bias in semi-supervised learning arises from both the problem itself and the inappropriate training with potentially incorrect pseudo labels, which accumulates the error in the iterative self-training process. To reduce the above bias, we propose Debiased Self-Training (DST). First, the generation and utilization of pseudo labels are decoupled by two parameter-independent classifier heads to avoid direct error accumulation. Second, we estimate the worst case of self-training bias, where the pseudo labeling function is accurate on labeled samples, yet makes as many mistakes as possible on unlabeled samples. We then adversarially optimize the representations to improve the quality of pseudo labels by avoiding the worst case. Extensive experiments justify that DST achieves an average improvement of 6.3% against state-of-the-art methods on standard semi-supervised learning benchmark datasets and 18.9%$ against FixMatch on 13 diverse tasks. Furthermore, DST can be seamlessly adapted to other self-training methods and help stabilize their training and balance performance across classes in both cases of training from scratch and finetuning from pre-trained models.
Deep neural networks have achieved great success in many important remote sensing tasks. Nevertheless, their vulnerability to adversarial examples should not be neglected. In this study, we systematically analyze the universal adversarial examples in remote sensing data for the first time, without any knowledge from the victim model. Specifically, we propose a novel black-box adversarial attack method, namely Mixup-Attack, and its simple variant Mixcut-Attack, for remote sensing data. The key idea of the proposed methods is to find common vulnerabilities among different networks by attacking the features in the shallow layer of a given surrogate model. Despite their simplicity, the proposed methods can generate transferable adversarial examples that deceive most of the state-of-the-art deep neural networks in both scene classification and semantic segmentation tasks with high success rates. We further provide the generated universal adversarial examples in the dataset named UAE-RS, which is the first dataset that provides black-box adversarial samples in the remote sensing field. We hope UAE-RS may serve as a benchmark that helps researchers to design deep neural networks with strong resistance toward adversarial attacks in the remote sensing field. Codes and the UAE-RS dataset are available online (https://github.com/YonghaoXu/UAE-RS).
This paper presents a task of audio-visual scene classification (SC) where input videos are classified into one of five real-life crowded scenes: 'Riot', 'Noise-Street', 'Firework-Event', 'Music-Event', and 'Sport-Atmosphere'. To this end, we firstly collect an audio-visual dataset (videos) of these five crowded contexts from Youtube (in-the-wild scenes). Then, a wide range of deep learning frameworks are proposed to deploy either audio or visual input data independently. Finally, results obtained from high-performed deep learning frameworks are fused to achieve the best accuracy score. Our experimental results indicate that audio and visual input factors independently contribute to the SC task's performance. Significantly, an ensemble of deep learning frameworks exploring either audio or visual input data can achieve the best accuracy of 95.7%.
The approach used not only challenges some of the fundamental mathematical techniques used so far in early experiments of the same trend but also introduces new scopes and new horizons for interesting results. The physics governing spectrograms have been optimized in the project along with exploring how it handles the intense requirements of the problem at hand. Major contributions and developments brought under the light, through this project involve using better mathematical techniques and problem-specific machine learning methods. Improvised data analysis and data augmentation for audio datasets like frequency masking and random frequency-time stretching are used in the project and hence are explained in this paper. In the used methodology, the audio transforms principle were also tried and explored, and indeed the insights gained were used constructively in the later stages of the project. Using a deep learning principle is surely one of them. Also, in this paper, the potential scopes and upcoming research openings in both short and long term tunnel of time has been presented. Although much of the results gained are domain-specific as of now, they are surely potent enough to produce novel solutions in various different domains of diverse backgrounds.
Due to the scarcity of labeled data, using supervised models pre-trained on ImageNet is a de facto standard in remote sensing scene classification. Recently, the availability of larger high resolution remote sensing (HRRS) image datasets and progress in self-supervised learning have brought up the questions of whether supervised ImageNet pre-training is still necessary for remote sensing scene classification and would supervised pre-training on HRRS image datasets or self-supervised pre-training on ImageNet achieve better results on target remote sensing scene classification tasks. To answer these questions, in this paper we both train models from scratch and fine-tune supervised and self-supervised ImageNet models on several HRRS image datasets. We also evaluate the transferability of learned representations to HRRS scene classification tasks and show that self-supervised pre-training outperforms the supervised one, while the performance of HRRS pre-training is similar to self-supervised pre-training or slightly lower. Finally, we propose using an ImageNet pre-trained model combined with a second round of pre-training using in-domain HRRS images, i.e. domain-adaptive pre-training. The experimental results show that domain-adaptive pre-training results in models that achieve state-of-the-art results on HRRS scene classification benchmarks. The source code and pre-trained models are available at \url{https://github.com/risojevicv/RSSC-transfer}.
The deployment of machine listening algorithms in real-life applications is often impeded by a domain shift caused for instance by different microphone characteristics. In this paper, we propose a novel domain adaptation strategy based on disentanglement learning. The goal is to disentangle task-specific and domain-specific characteristics in the analyzed audio recordings. In particular, we combine two strategies: First, we apply different binary masks to internal embedding representations and, second, we suggest a novel combination of categorical cross-entropy and variance-based losses. Our results confirm the disentanglement of both tasks on an embedding level but show only minor improvement in the acoustic scene classification performance, when training data from both domains can be used. As a second finding, we can confirm the effectiveness of a state-of-the-art unsupervised domain adaptation strategy, which performs across-domain adaptation on a feature-level instead.
We propose a variational Bayesian (VB) approach to learning distributions of latent variables in deep neural network (DNN) models for cross-domain knowledge transfer, to address acoustic mismatches between training and testing conditions. Instead of carrying out point estimation in conventional maximum a posteriori estimation with a risk of having a curse of dimensionality in estimating a huge number of model parameters, we focus our attention on estimating a manageable number of latent variables of DNNs via a VB inference framework. To accomplish model transfer, knowledge learnt from a source domain is encoded in prior distributions of latent variables and optimally combined, in a Bayesian sense, with a small set of adaptation data from a target domain to approximate the corresponding posterior distributions. Experimental results on device adaptation in acoustic scene classification show that our proposed VB approach can obtain good improvements on target devices, and consistently outperforms 13 state-of-the-art knowledge transfer algorithms.
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.
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.
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 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.
Image classification is one of the main drivers of the rapid developments in deep learning with convolutional neural networks for computer vision. So is the analogous task of scene classification in remote sensing. However, in contrast to the computer vision community that has long been using well-established, large-scale standard datasets to train and benchmark high-capacity models, the remote sensing community still largely relies on relatively small and often application-dependend datasets, thus lacking comparability. With this letter, we present a classification-oriented conversion of the SEN12MS dataset. Using that, we provide results for several baseline models based on two standard CNN architectures and different input data configurations. Our results support the benchmarking of remote sensing image classification and provide insights to the benefit of multi-spectral data and multi-sensor data fusion over conventional RGB imagery.
Scene recognition is one of the basic problems in computer vision research with extensive applications in robotics. When available, depth images provide helpful geometric cues that complement the RGB texture information and help to identify discriminative scene image features. Depth sensing technology developed fast in the last years and a great variety of 3D cameras have been introduced, each with different acquisition properties. However, those properties are often neglected when targeting big data collections, so multi-modal images are gathered disregarding their original nature. In this work, we put under the spotlight the existence of a possibly severe domain shift issue within multi-modality scene recognition datasets. As a consequence, a scene classification model trained on one camera may not generalize on data from a different camera, only providing a low recognition performance. Starting from the well-known SUN RGB-D dataset, we designed an experimental testbed to study this problem and we use it to benchmark the performance of existing methods. Finally, we introduce a novel adaptive scene recognition approach that leverages self-supervised translation between modalities. Indeed, learning to go from RGB to depth and vice-versa is an unsupervised procedure that can be trained jointly on data of multiple cameras and may help to bridge the gap among the extracted feature distributions. Our experimental results confirm the effectiveness of the proposed approach.
Supervised learning techniques are at the center of many tasks in remote sensing. Unfortunately, these methods, especially recent deep learning methods, often require large amounts of labeled data for training. Even though satellites acquire large amounts of data, labeling the data is often tedious, expensive and requires expert knowledge. Hence, improved methods that require fewer labeled samples are needed. We present MSMatch, the first semi-supervised learning approach competitive with supervised methods on scene classification on the EuroSAT and UC Merced Land Use benchmark datasets. We test both RGB and multispectral images of EuroSAT and perform various ablation studies to identify the critical parts of the model. The trained neural network achieves state-of-the-art results on EuroSAT with an accuracy that is up to 19.76% better than previous methods depending on the number of labeled training examples. With just five labeled examples per class, we reach 94.53% and 95.86% accuracy on the EuroSAT RGB and multispectral datasets, respectively. On the UC Merced Land Use dataset, we outperform previous works by up to 5.59% and reach 90.71% with five labeled examples. Our results show that MSMatch is capable of greatly reducing the requirements for labeled data. It translates well to multispectral data and should enable various applications that are currently infeasible due to a lack of labeled data. We provide the source code of MSMatch online to enable easy reproduction and quick adoption.
The majority of sound scene analysis work focuses on one of two clearly defined tasks: acoustic scene classification or sound event detection. Whilst this separation of tasks is useful for problem definition, they inherently ignore some subtleties of the real-world, in particular how humans vary in how they describe a scene. Some will describe the weather and features within it, others will use a holistic descriptor like `park', and others still will use unique identifiers such as cities or names. In this paper, we undertake the task of automatic city classification to ask whether we can recognize a city from a set of sound scenes? In this problem each city has recordings from multiple scenes. We test a series of methods for this novel task and show that a simple convolutional neural network (CNN) can achieve accuracy of 50%. This is less than the acoustic scene classification task baseline in the DCASE 2018 ASC challenge on the same data. A simple adaptation to the class labels of pairing city labels with grouped scenes, accuracy increases to 52%, closer to the simpler scene classification task. Finally we also formulate the problem in a multi-task learning framework and achieve an accuracy of 56%, outperforming the aforementioned approaches.
Deep Neural Networks are known to be very demanding in terms of computing and memory requirements. Due to the ever increasing use of embedded systems and mobile devices with a limited resource budget, designing low-complexity models without sacrificing too much of their predictive performance gained great importance. In this work, we investigate and compare several well-known methods to reduce the number of parameters in neural networks. We further put these into the context of a recent study on the effect of the Receptive Field (RF) on a model's performance, and empirically show that we can achieve high-performing low-complexity models by applying specific restrictions on the RFs, in combination with parameter reduction methods. Additionally, we propose a filter-damping technique for regularizing the RF of models, without altering their architecture and changing their parameter counts. We will show that incorporating this technique improves the performance in various low-complexity settings such as pruning and decomposed convolution. Using our proposed filter damping, we achieved the 1st rank at the DCASE-2020 Challenge in the task of Low-Complexity Acoustic Scene Classification.