Existing polarimetric synthetic aperture radar (PolSAR) image classification methods cannot achieve satisfactory performance on complex scenes characterized by several types of land cover with significant levels of noise or similar scattering properties across land cover types. Hence, we propose a supervised classification method aimed at constructing a classifier based on self-paced learning (SPL). SPL has been demonstrated to be effective at dealing with complex data while providing classifier. In this paper, a novel Support Vector Machine (SVM) algorithm based on SPL with neighborhood constraints (SVM_SPLNC) is proposed. The proposed method leverages the easiest samples first to obtain an initial parameter vector. Then, more complex samples are gradually incorporated to update the parameter vector iteratively. Moreover, neighborhood constraints are introduced during the training process to further improve performance. Experimental results on three real PolSAR images show that the proposed method performs well on complex scenes.
Recently, data-driven deep saliency models have achieved high performance and have outperformed classical saliency models, as demonstrated by results on datasets such as the MIT300 and SALICON. Yet, there remains a large gap between the performance of these models and the inter-human baseline. Some outstanding questions include what have these models learned, how and where they fail, and how they can be improved. This article attempts to answer these questions by analyzing the representations learned by individual neurons located at the intermediate layers of deep saliency models. To this end, we follow the steps of existing deep saliency models, that is borrowing a pre-trained model of object recognition to encode the visual features and learning a decoder to infer the saliency. We consider two cases when the encoder is used as a fixed feature extractor and when it is fine-tuned, and compare the inner representations of the network. To study how the learned representations depend on the task, we fine-tune the same network using the same image set but for two different tasks: saliency prediction versus scene classification. Our analyses reveal that: 1) some visual regions (e.g. head, text, symbol, vehicle) are already encoded within various layers of the network pre-trained for object recognition, 2) using modern datasets, we find that fine-tuning pre-trained models for saliency prediction makes them favor some categories (e.g. head) over some others (e.g. text), 3) although deep models of saliency outperform classical models on natural images, the converse is true for synthetic stimuli (e.g. pop-out search arrays), an evidence of significant difference between human and data-driven saliency models, and 4) we confirm that, after-fine tuning, the change in inner-representations is mostly due to the task and not the domain shift in the data.
Learning powerful discriminative features for remote sensing image scene classification is a challenging computer vision problem. In the past, most classification approaches were based on handcrafted features. However, most recent approaches to remote sensing scene classification are based on Convolutional Neural Networks (CNNs). The de facto practice when learning these CNN models is only to use original RGB patches as input with training performed on large amounts of labeled data (ImageNet). In this paper, we show class activation map (CAM) encoded CNN models, codenamed DDRL-AM, trained using original RGB patches and attention map based class information provide complementary information to the standard RGB deep models. To the best of our knowledge, we are the first to investigate attention information encoded CNNs. Additionally, to enhance the discriminability, we further employ a recently developed object function called "center loss," which has proved to be very useful in face recognition. Finally, our framework provides attention guidance to the model in an end-to-end fashion. Extensive experiments on two benchmark datasets show that our approach matches or exceeds the performance of other methods.
This paper presents the BigEarthNet that is a new large-scale multi-label Sentinel-2 benchmark archive. The BigEarthNet consists of 590,326 Sentinel-2 image patches, each of which is a section of i) 120x120 pixels for 10m bands; ii) 60x60 pixels for 20m bands; and iii) 20x20 pixels for 60m bands. Unlike most of the existing archives, each image patch is annotated by multiple land-cover classes (i.e., multi-labels) that are provided from the CORINE Land Cover database of the year 2018 (CLC 2018). The BigEarthNet is significantly larger than the existing archives in remote sensing (RS) and thus is much more convenient to be used as a training source in the context of deep learning. This paper first addresses the limitations of the existing archives and then describes the properties of the BigEarthNet. Experimental results obtained in the framework of RS image scene classification problems show that a shallow Convolutional Neural Network (CNN) architecture trained on the BigEarthNet provides much higher accuracy compared to a state-of-the-art CNN model pre-trained on the ImageNet (which is a very popular large-scale benchmark archive in computer vision). The BigEarthNet opens up promising directions to advance operational RS applications and research in massive Sentinel-2 image archives.
In this paper, we propose a novel approach that learns to sequentially attend to different Convolutional Neural Networks (CNN) layers (i.e., ``what'' feature abstraction to attend to) and different spatial locations of the selected feature map (i.e., ``where'') to perform the task at hand. Specifically, at each Recurrent Neural Network (RNN) step, both a CNN layer and localized spatial region within it are selected for further processing. We demonstrate the effectiveness of this approach on two computer vision tasks: (i) image-based six degree of freedom camera pose regression and (ii) indoor scene classification. Empirically, we show that combining the ``what'' and ``where'' aspects of attention improves network performance on both tasks. We evaluate our method on standard benchmarks for camera localization (Cambridge, 7-Scenes, and TUM-LSI) and for scene classification (MIT-67 Indoor Scenes). For camera localization our approach reduces the median error by 18.8\% for position and 8.2\% for orientation (averaged over all scenes), and for scene classification it improves the mean accuracy by 3.4\% over previous methods.
Acoustic scene classification is the task of identifying the scene from which the audio signal is recorded. Convolutional neural network (CNN) models are widely adopted with proven successes in acoustic scene classification. However, there is little insight on how an audio scene is perceived in CNN, as what have been demonstrated in image recognition research. In the present study, the Class Activation Mapping (CAM) is utilized to analyze how the log-magnitude Mel-scale filter-bank (log-Mel) features of different acoustic scenes are learned in a CNN classifier. It is noted that distinct high-energy time-frequency components of audio signals generally do not correspond to strong activation on CAM, while the background sound texture are well learned in CNN. In order to make the sound texture more salient, we propose to apply the Difference of Gaussian (DoG) and Sobel operator to process the log-Mel features and enhance edge information of the time-frequency image. Experimental results on the DCASE 2017 ASC challenge show that using edge enhanced log-Mel images as input feature of CNN significantly improves the performance of audio scene classification.
Cloud-based overlays are often present in optical remote sensing images, thus limiting the application of acquired data. Removing clouds is an indispensable pre-processing step in remote sensing image analysis. Deep learning has achieved great success in the field of remote sensing in recent years, including scene classification and change detection. However, deep learning is rarely applied in remote sensing image removal clouds. The reason is the lack of data sets for training neural networks. In order to solve this problem, this paper first proposed the Remote sensing Image Cloud rEmoving dataset (RICE). The proposed dataset consists of two parts: RICE1 contains 500 pairs of images, each pair has images with cloud and cloudless size of 512*512; RICE2 contains 450 sets of images, each set contains three 512*512 size images. , respectively, the reference picture without clouds, the picture of the cloud and the mask of its cloud. The dataset is freely available at \url{https://github.com/BUPTLdy/RICE_DATASET}.
Computer vision systems currently lack the ability to reliably recognize artistically rendered objects, especially when such data is limited. In this paper, we propose a method for recognizing objects in artistic modalities (such as paintings, cartoons, or sketches), without requiring any labeled data from those modalities. Our method explicitly accounts for stylistic domain shifts between and within domains. To do so, we introduce a complementary training modality constructed to be similar in artistic style to the target domain, and enforce that the network learns features that are invariant between the two training modalities. We show how such artificial labeled source domains can be generated automatically through the use of style transfer techniques, using diverse target images to represent the style in the target domain. Unlike existing methods which require a large amount of unlabeled target data, our method can work with as few as ten unlabeled images. We evaluate it on a number of cross-domain object and scene classification tasks and on a new dataset we release. Our experiments show that our approach, though conceptually simple, significantly improves the accuracy that existing domain adaptation techniques obtain for artistic object recognition.
The computer vision community has witnessed recent advances in scene categorization from images, with the state-of-the art systems now achieving impressive recognition rates on challenging benchmarks such as the Places365 dataset. Such systems have been trained on photographs which include color, texture and shading cues. The geometry of shapes and surfaces, as conveyed by scene contours, is not explicitly considered for this task. Remarkably, humans can accurately recognize natural scenes from line drawings, which consist solely of contour-based shape cues. Here we report the first computer vision study on scene categorization of line drawings derived from popular databases including an artist scene database, MIT67, and Places365. Specifically, we use off-the-shelf pre-trained CNNs to perform scene classification given only contour information as input and find performance levels well above chance. We also show that medial-axis based contour salience methods can be used to select more informative subsets of contour pixels and that the variation in CNN classification performance on various choices for these subsets is qualitatively similar to that observed in human performance. Moreover, when the salience measures are used to weight the contours, as opposed to pruning them, we find that these weights boost our CNN performance above that for unweighted contour input. That is, the medial axis based salience weights appear to add useful information that is not available when CNNs are trained to use contours alone.
Due to the variability in characteristics of audio scenes, some scenes can naturally be recognized earlier than others. In this work, rather than using equal-length snippets for all scene categories, as is common in the literature, we study to which temporal extent an audio scene can be reliably recognized given state-of-the-art models. Moreover, as model fusion with deep network ensemble is prevalent in audio scene classification, we further study whether, and if so, when model fusion is necessary for this task. To achieve these goals, we employ two single-network systems relying on a convolutional neural network and a recurrent neural network for classification as well as early fusion and late fusion of these networks. Experimental results on the LITIS-Rouen dataset show that some scenes can be reliably recognized with a few seconds while other scenes require significantly longer durations. In addition, model fusion is shown to be the most beneficial when the signal length is short.
We investigate supervised learning strategies that improve the training of neural network audio classifiers on small annotated collections. In particular, we study whether (i) a naive regularization of the solution space, (ii) prototypical networks, (iii) transfer learning, or (iv) their combination, can foster deep learning models to better leverage a small amount of training examples. To this end, we evaluate (i-iv) for the tasks of acoustic event recognition and acoustic scene classification, considering from 1 to 100 labeled examples per class. Results indicate that transfer learning is a powerful strategy in such scenarios, but prototypical networks show promising results when one does not count with external or validation data.
Lack of annotated samples greatly restrains the direct application of deep learning in remote sensing image scene classification. Although researches have been done to tackle this issue by data augmentation with various image transformation operations, they are still limited in quantity and diversity. Recently, the advent of the unsupervised learning based generative adversarial networks (GANs) bring us a new way to generate augmented samples. However, such GAN-generated samples are currently only served for training GANs model itself and for improving the performance of the discriminator in GANs internally (in vivo). It becomes a question of serious doubt whether the GAN-generated samples can help better improve the scene classification performance of other deep learning networks (in vitro), compared with the widely used transformed samples. To answer this question, this paper proposes a SiftingGAN approach to generate more numerous, more diverse and more authentic labeled samples for data augmentation. SiftingGAN extends traditional GAN framework with an Online-Output method for sample generation, a Generative-Model-Sifting method for model sifting, and a Labeled-Sample-Discriminating method for sample sifting. Experiments on the well-known AID dataset demonstrate that the proposed SiftingGAN method can not only effectively improve the performance of the scene classification baseline that is achieved without data augmentation, but also significantly excels the comparison methods based on traditional geometric/radiometric transformation operations.
In this project, we adapt high-performing CNN architectures to differentiate between scenes with and without abandoned luggage. Using frames from two video datasets, we compare the results of training different architectures on each dataset as well as on combining the datasets. We additionally use network visualization techniques to gain insight into what the neural network sees, and the basis of the classification decision. We intend that our results benefit further work in applying CNNs in surveillance and security-related tasks.
Spectrograms have been widely used in Convolutional Neural Networks based schemes for acoustic scene classification, such as the STFT spectrogram and the MFCC spectrogram, etc. They have different time-frequency characteristics, contributing to their own advantages and disadvantages in recognizing acoustic scenes. In this letter, a novel multi-spectrogram fusion framework is proposed, making the spectrograms complement each other. In the framework, a single CNN architecture is applied onto multiple spectrograms for feature extraction. The deep features extracted from multiple spectrograms are then fused to discriminate the acoustic scenes. Moreover, motivated by the inter-class similarities in acoustic scene datasets, a label expansion method is further proposed in which super-class labels are constructed upon the original classes. On the help of the expanded labels, the CNN models are transformed into the multitask learning form to improve the acoustic scene classification by appending the auxiliary task of super-class classification. To verify the effectiveness of the proposed methods, intensive experiments have been performed on the DCASE2017 and the LITIS Rouen datasets. Experimental results show that the proposed method can achieve promising accuracies on both datasets. Specifically, accuracies of 0.9744, 0.8865 and 0.7778 are obtained for the LITIS Rouen dataset, the DCASE Development set and Evaluation set respectively.
A general problem in acoustic scene classification task is the mismatched conditions between training and testing data, which significantly reduces the performance of the developed methods on classification accuracy. As a countermeasure, we present the first method of unsupervised adversarial domain adaptation for acoustic scene classification. We employ a model pre-trained on data from one set of conditions and by using data from other set of conditions, we adapt the model in order that its output cannot be used for classifying the set of conditions that input data belong to. We use a freely available dataset from the DCASE 2018 challenge Task 1, subtask B, that contains data from mismatched recording devices. We consider the scenario where the annotations are available for the data recorded from one device, but not for the rest. Our results show that with our model agnostic method we can achieve $\sim 10\%$ increase at the accuracy on an unseen and unlabeled dataset, while keeping almost the same performance on the labeled dataset.
In this paper we study the problem of acoustic scene classification, i.e., categorization of audio sequences into mutually exclusive classes based on their spectral content. We describe the methods and results discovered during a competition organized in the context of a graduate machine learning course; both by the students and external participants. We identify the most suitable methods and study the impact of each by performing an ablation study of the mixture of approaches. We also compare the results with a neural network baseline, and show the improvement over that. Finally, we discuss the impact of using a competition as a part of a university course, and justify its importance in the curriculum based on student feedback.
This paper presents a new deep learning approach for video-based scene classification. We design a Heterogeneous Deep Discriminative Model (HDDM) whose parameters are initialized by performing an unsupervised pre-training in a layer-wise fashion using Gaussian Restricted Boltzmann Machines (GRBM). In order to avoid the redundancy of adjacent frames, we extract spatiotemporal variation patterns within frames and represent them sparsely using Sparse Cubic Symmetrical Pattern (SCSP). Then, a pre-initialized HDDM is separately trained using the videos of each class to learn class-specific models. According to the minimum reconstruction error from the learnt class-specific models, a weighted voting strategy is employed for the classification. The performance of the proposed method is extensively evaluated on two action recognition datasets; UCF101 and Hollywood II, and three dynamic texture and dynamic scene datasets; DynTex, YUPENN, and Maryland. The experimental results and comparisons against state-of-the-art methods demonstrate that the proposed method consistently achieves superior performance on all datasets.
While there has been significant progress in solving the problems of image pixel labeling, object detection and scene classification, existing approaches normally address them separately. In this paper, we propose to tackle these problems from a bottom-up perspective, where we simply need a semantic segmentation of the scene as input. We employ the DeepLab architecture, based on the ResNet deep network, which leverages multi-scale inputs to later fuse their responses to perform a precise pixel labeling of the scene. This semantic segmentation mask is used to localize the objects and to recognize the scene, following two simple yet effective strategies. We evaluate the benefits of our solutions, performing a thorough experimental evaluation on the NYU Depth V2 dataset. Our approach achieves a performance that beats the leading results by a significant margin, defining the new state of the art in this benchmark for the three tasks comprising the scene understanding: semantic segmentation, object detection and scene categorization.
In acoustic scene classification researches, audio segment is usually split into multiple samples. Majority voting is then utilized to ensemble the results of the samples. In this paper, we propose a punishment voting algorithm based on the super categories construction method for acoustic scene classification. Specifically, we propose a DenseNet-like model as the base classifier. The base classifier is trained by the CQT spectrograms generated from the raw audio segments. Taking advantage of the results of the base classifier, we propose a super categories construction method using the spectral clustering. Super classifiers corresponding to the constructed super categories are further trained. Finally, the super classifiers are utilized to enhance the majority voting of the base classifier by punishment voting. Experiments show that the punishment voting obviously improves the performances on both the DCASE2017 Development dataset and the LITIS Rouen dataset.
Registering images from different modalities is an active area of research in computer aided medical interventions. Several registration algorithms have been developed, many of which achieve high accuracy. However, these results are dependent on many factors, including the quality of the extracted features or segmentations being registered as well as the initial alignment. Although several methods have been developed towards improving segmentation algorithms and automating the segmentation process, few automatic initialization algorithms have been explored. In many cases, the initial alignment from which a registration is initiated is performed manually, which interferes with the clinical workflow. Our aim is to use scene classification in endoscopic procedures to achieve coarse alignment of the endoscope and a preoperative image of the anatomy. In this paper, we show using simulated scenes that a neural network can predict the region of anatomy (with respect to a preoperative image) that the endoscope is located in by observing a single endoscopic video frame. With limited training and without any hyperparameter tuning, our method achieves an accuracy of 76.53 (+/-1.19)%. There are several avenues for improvement, making this a promising direction of research. Code is available at https://github.com/AyushiSinha/AutoInitialization.