Treating images as data has become increasingly popular in political science. While existing classifiers for images reach high levels of accuracy, it is difficult to systematically assess the visual features on which they base their classification. This paper presents a two-level classification method that addresses this transparency problem. At the first stage, an image segmenter detects the objects present in the image and a feature vector is created from those objects. In the second stage, this feature vector is used as input for standard machine learning classifiers to discriminate between images. We apply this method to a new dataset of more than 140,000 images to detect which ones display political protest. This analysis demonstrates three advantages to this paper's approach. First, identifying objects in images improves transparency by providing human-understandable labels for the objects shown on an image. Second, knowing these objects enables analysis of which distinguish protest images from non-protest ones. Third, comparing the importance of objects across countries reveals how protest behavior varies. These insights are not available using conventional computer vision classifiers and provide new opportunities for comparative research.
Image classification is the task of assigning to an input image a label from a fixed set of categories. One of its most important applicative fields is that of robotics, in particular the needing of a robot to be aware of what's around and the consequent exploitation of that information as a benefit for its tasks. In this work we consider the problem of a robot that enters a new environment and wants to understand visual data coming from its camera, so to extract knowledge from them. As main novelty we want to overcome the needing of a physical robot, as it could be expensive and unhandy, so to hopefully enhance, speed up and ease the research in this field. That's why we propose to develop an application for a mobile platform that wraps several deep visual recognition tasks. First we deal with a simple Image classification, testing a model obtained from an AlexNet trained on the ILSVRC 2012 dataset. Several photo settings are considered to better understand which factors affect most the quality of classification. For the same purpose we are interested to integrate the classification task with an extra module dealing with segmentation of the object inside the image. In particular we propose a technique for extracting the object shape and moving out all the background, so to focus the classification only on the region occupied by the object. Another significant task that is included is that of object discovery. Its purpose is to simulate the situation in which the robot needs a certain object to complete one of its activities. It starts searching for what it needs by looking around and trying to understand the location of the object by scanning the surrounding environment. Finally we provide a tool for dealing with the creation of customized task-specific databases, meant to better suit to one's needing in a particular vision task.
In this work, we exploit convolutional neural networks (CNNs) for the classification of very high resolution (VHR) polarimetric SAR (PolSAR) data. Due to the significant appearance of heterogeneous textures within these data, not only polarimetric features but also structural tensors are exploited to feed CNN models. For deep networks, we use the SegNet model for semantic segmentation, which corresponds to pixelwise classification in remote sensing. Our experiments on the airborne F-SAR data show that for VHR PolSAR images, SegNet could provide high accuracy for the classification task; and introducing structural tensors together with polarimetric features as inputs could help the network to focus more on geometrical information to significantly improve the classification performance.
Whether it is computer vision, natural language processing or speech recognition, the essence of these applications is to obtain powerful feature representations that make downstream applications completion more efficient. Taking image recognition as an example, whether it is hand-crafted low-level feature representation or feature representation extracted by a convolutional neural networks(CNNs), the goal is to extract features that better represent image features, thereby improving classification accuracy. However, we observed that image feature representations share a large common vector and a few top dominating directions. To address this problems, we propose a simple but effective postprocessing method to render off-the-shelf feature representations even stronger by eliminating the common mean vector from off-the-shelf feature representations. The postprocessing is empirically validated on a variety of datasets and feature extraction methods.such as VGG, LBP, and HOG. Some experiments show that the features that have been post-processed by postprocessing algorithm can get better results than original ones.
The identification of out-of-distribution data is vital to the deployment of classification networks. For example, a generic neural network that has been trained to differentiate between images of dogs and cats can only classify an input as either a dog or a cat. If a picture of a car or a kumquat were to be supplied to this classifier, the result would still be either a dog or a cat. In order to mitigate this, techniques such as the neural network watchdog have been developed. The compression of the image input into the latent layer of the autoencoder defines the region of in-distribution in the image space. This in-distribution set of input data has a corresponding boundary in the image space. The watchdog assesses whether inputs are in inside or outside this boundary. This paper demonstrates how to sharpen this boundary using generative network training data augmentation thereby bettering the discrimination and overall performance of the watchdog.
Convolutional Neural Networks (CNN) increase depth by stacking convolutional layers, and deeper network models perform better in image recognition. Empirical research shows that simply stacking convolutional layers does not make the network train better, and skip connection (residual learning) can improve network model performance. For the image classification task, models with global densely connected architectures perform well in large datasets like ImageNet, but are not suitable for small datasets such as CIFAR-10 and SVHN. Different from dense connections, we propose two new algorithms to connect layers. Baseline is a densely connected network, and the networks connected by the two new algorithms are named ShortNet1 and ShortNet2 respectively. The experimental results of image classification on CIFAR-10 and SVHN show that ShortNet1 has a 5% lower test error rate and 25% faster inference time than Baseline. ShortNet2 speeds up inference time by 40% with less loss in test accuracy. Code and pre-trained models are available at https://github.com/RuiyangJu/Connection_Reduction.
We developed a rapid scanning optical microscope, termed "BlurryScope", that leverages continuous image acquisition and deep learning to provide a cost-effective and compact solution for automated inspection and analysis of tissue sections. BlurryScope integrates specialized hardware with a neural network-based model to quickly process motion-blurred histological images and perform automated pathology classification. This device offers comparable speed to commercial digital pathology scanners, but at a significantly lower price point and smaller size/weight, making it ideal for fast triaging in small clinics, as well as for resource-limited settings. To demonstrate the proof-of-concept of BlurryScope, we implemented automated classification of human epidermal growth factor receptor 2 (HER2) scores on immunohistochemically (IHC) stained breast tissue sections, achieving concordant results with those obtained from a high-end digital scanning microscope. We evaluated this approach by scanning HER2-stained tissue microarrays (TMAs) at a continuous speed of 5 mm/s, which introduces bidirectional motion blur artifacts. These compromised images were then used to train our network models. Using a test set of 284 unique patient cores, we achieved blind testing accuracies of 79.3% and 89.7% for 4-class (0, 1+, 2+, 3+) and 2-class (0/1+ , 2+/3+) HER2 score classification, respectively. BlurryScope automates the entire workflow, from image scanning to stitching and cropping of regions of interest, as well as HER2 score classification. We believe BlurryScope has the potential to enhance the current pathology infrastructure in resource-scarce environments, save diagnostician time and bolster cancer identification and classification across various clinical environments.
Image classifiers based on convolutional neural networks are defined, and the rate of convergence of the misclassification risk of the estimates towards the optimal misclassification risk is analyzed. Under suitable assumptions on the smoothness and structure of the aposteriori probability a rate of convergence is shown which is independent of the dimension of the image. This proves that in image classification it is possible to circumvent the curse of dimensionality by convolutional neural networks.
In deep learning area, large-scale image datasets bring a breakthrough in the success of object recognition and retrieval. Nowadays, as the embodiment of innovation, the diversity of the industrial goods is significantly larger, in which the incomplete multiview, multimodal and multilabel are different from the traditional dataset. In this paper, we introduce an industrial goods dataset, namely PatentNet, with numerous highly diverse, accurate and detailed annotations of industrial goods images, and corresponding texts. In PatentNet, the images and texts are sourced from design patent. Within over 6M images and corresponding texts of industrial goods labeled manually checked by professionals, PatentNet is the first ongoing industrial goods image database whose varieties are wider than industrial goods datasets used previously for benchmarking. PatentNet organizes millions of images into 32 classes and 219 subclasses based on the Locarno Classification Agreement. Through extensive experiments on image classification, image retrieval and incomplete multiview clustering, we demonstrate that our PatentNet is much more diverse, complex, and challenging, enjoying higher potentials than existing industrial image datasets. Furthermore, the characteristics of incomplete multiview, multimodal and multilabel in PatentNet are able to offer unparalleled opportunities in the artificial intelligence community and beyond.
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.
Existing interpretation algorithms have found that, even deep models make the same and right predictions on the same image, they might rely on different sets of input features for classification. However, among these sets of features, some common features might be used by the majority of models. In this paper, we are wondering what are the common features used by various models for classification and whether the models with better performance may favor those common features. For this purpose, our works uses an interpretation algorithm to attribute the importance of features (e.g., pixels or superpixels) as explanations, and pro- poses the cross-model consensus of explanations to capture the common features. Specifically, we first prepare a set of deep models as a committee, then deduce the explanation for every model, and obtain the consensus of explanations across the entire committee through voting. With the cross-model consensus of explanations, we conduct extensive experiments using 80+ models on 5 datasets/tasks. We find three interesting phenomena as follows: (1) the consensus obtained from image classification models is aligned with the ground truth of semantic segmentation; (2) we measure the similarity of the explanation result of each model in the committee to the consensus (namely consensus score), and find positive correlations between the consensus score and model performance; and (3) the consensus score coincidentally correlates to the interpretability.
In this paper, we propose a constrained linear data-feature mapping model as an interpretable mathematical model for image classification using convolutional neural network (CNN) such as the ResNet. From this viewpoint, we establish the detailed connections in a technical level between the traditional iterative schemes for constrained linear system and the architecture for the basic blocks of ResNet. Under these connections, we propose some natural modifications of ResNet type models which will have less parameters but still maintain almost the same accuracy as these corresponding original models. Some numerical experiments are shown to demonstrate the validity of this constrained learning data-feature mapping assumption.
Face verification is a relatively easy task with the help of discriminative features from deep neural networks. However, it is still a challenge to recognize faces on millions of identities while keeping high performance and efficiency. The challenge 2 of MS-Celeb-1M is a classification task. However, the number of identities is too large and it is not that elegant to treat the task as an image classification task. We treat the classification task as similarity search and do experiments on different similarity search strategies. Similarity search strategy accelerates the speed of searching and boosts the accuracy of final results. The model used for extracting features is a single deep neural network pretrained on CASIA-Webface, which is not trained on the base set or novel set offered by official. Finally, we rank \textbf{3rd}, while the speed of searching is 1ms/image.
We propose a new approach to natural language understanding in which we consider the input text as an image and apply 2D Convolutional Neural Networks to learn the local and global semantics of the sentences from the variations ofthe visual patterns of words. Our approach demonstrates that it is possible to get semantically meaningful features from images with text without using optical character recognition and sequential processing pipelines, techniques that traditional Natural Language Understanding algorithms require. To validate our approach, we present results for two applications: text classification and dialog modeling. Using a 2D Convolutional Neural Network, we were able to outperform the state-of-art accuracy results of non-Latin alphabet-based text classification and achieved promising results for eight text classification datasets. Furthermore, our approach outperformed the memory networks when using out of vocabulary entities fromtask 4 of the bAbI dialog dataset.
Deep Convolutional Neural Networks (CNNs) are empirically known to be invariant to moderate translation but not to rotation in image classification. This paper proposes a deep CNN model, called CyCNN, which exploits polar mapping of input images to convert rotation to translation. To deal with the cylindrical property of the polar coordinates, we replace convolution layers in conventional CNNs to cylindrical convolutional (CyConv) layers. A CyConv layer exploits the cylindrically sliding windows (CSW) mechanism that vertically extends the input-image receptive fields of boundary units in a convolutional layer. We evaluate CyCNN and conventional CNN models for classification tasks on rotated MNIST, CIFAR-10, and SVHN datasets. We show that if there is no data augmentation during training, CyCNN significantly improves classification accuracies when compared to conventional CNN models. Our implementation of CyCNN is publicly available on https://github.com/mcrl/CyCNN.
eXplanation Based Learning (XBL) is a form of Interactive Machine Learning (IML) that provides a model refining approach via user feedback collected on model explanations. Although the interactivity of XBL promotes model transparency, XBL requires a huge amount of user interaction and can become expensive as feedback is in the form of detailed annotation rather than simple category labelling which is more common in IML. This expense is exacerbated in high stakes domains such as medical image classification. To reduce the effort and expense of XBL we introduce a new approach that uses two input instances and their corresponding Gradient Weighted Class Activation Mapping (GradCAM) model explanations as exemplary explanations to implement XBL. Using a medical image classification task, we demonstrate that, using minimal human input, our approach produces improved explanations (+0.02, +3%) and achieves reduced classification performance (-0.04, -4%) when compared against a model trained without interactions.
In this thesis, we develop theoretical, algorithmic and experimental contributions for Machine Learning with limited labels, and more specifically for the tasks of Image Classification and Object Detection in Computer Vision. In a first contribution, we are interested in bridging the gap between theory and practice for popular Meta-Learning algorithms used in Few-Shot Classification. We make connections to Multi-Task Representation Learning, which benefits from solid theoretical foundations, to verify the best conditions for a more efficient meta-learning. Then, to leverage unlabeled data when training object detectors based on the Transformer architecture, we propose both an unsupervised pretraining and a semi-supervised learning method in two other separate contributions. For pretraining, we improve Contrastive Learning for object detectors by introducing the localization information. Finally, our semi-supervised method is the first tailored to transformer-based detectors.
Although complex-valued (CV) neural networks have shown better classification results compared to their real-valued (RV) counterparts for polarimetric synthetic aperture radar (PolSAR) classification, the extension of pixel-level RV networks to the complex domain has not yet thoroughly examined. This paper presents a novel complex-valued deep fully convolutional neural network (CV-FCN) designed for PolSAR image classification. Specifically, CV-FCN uses PolSAR CV data that includes the phase information and utilizes the deep FCN architecture that performs pixel-level labeling. It integrates the feature extraction module and the classification module in a united framework. Technically, for the particularity of PolSAR data, a dedicated complex-valued weight initialization scheme is defined to initialize CV-FCN. It considers the distribution of polarization data to conduct CV-FCN training from scratch in an efficient and fast manner. CV-FCN employs a complex downsampling-then-upsampling scheme to extract dense features. To enrich discriminative information, multi-level CV features that retain more polarization information are extracted via the complex downsampling scheme. Then, a complex upsampling scheme is proposed to predict dense CV labeling. It employs complex max-unpooling layers to greatly capture more spatial information for better robustness to speckle noise. In addition, to achieve faster convergence and obtain more precise classification results, a novel average cross-entropy loss function is derived for CV-FCN optimization. Experiments on real PolSAR datasets demonstrate that CV-FCN achieves better classification performance than other state-of-art methods.
We present a novel technique to automatically colorize grayscale images that combines both global priors and local image features. Based on Convolutional Neural Networks, our deep network features a fusion layer that allows us to elegantly merge local information dependent on small image patches with global priors computed using the entire image. The entire framework, including the global and local priors as well as the colorization model, is trained in an end-to-end fashion. Furthermore, our architecture can process images of any resolution, unlike most existing approaches based on CNN. We leverage an existing large-scale scene classification database to train our model, exploiting the class labels of the dataset to more efficiently and discriminatively learn the global priors. We validate our approach with a user study and compare against the state of the art, where we show significant improvements. Furthermore, we demonstrate our method extensively on many different types of images, including black-and-white photography from over a hundred years ago, and show realistic colorizations.
Image Transformer has recently achieved significant progress for natural image understanding, either using supervised (ViT, DeiT, etc.) or self-supervised (BEiT, MAE, etc.) pre-training techniques. In this paper, we propose \textbf{DiT}, a self-supervised pre-trained \textbf{D}ocument \textbf{I}mage \textbf{T}ransformer model using large-scale unlabeled text images for Document AI tasks, which is essential since no supervised counterparts ever exist due to the lack of human-labeled document images. We leverage DiT as the backbone network in a variety of vision-based Document AI tasks, including document image classification, document layout analysis, table detection as well as text detection for OCR. Experiment results have illustrated that the self-supervised pre-trained DiT model achieves new state-of-the-art results on these downstream tasks, e.g. document image classification (91.11 $\rightarrow$ 92.69), document layout analysis (91.0 $\rightarrow$ 94.9), table detection (94.23 $\rightarrow$ 96.55) and text detection for OCR (93.07 $\rightarrow$ 94.29). The code and pre-trained models are publicly available at \url{https://aka.ms/msdit}.