Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) is the key technique for remote sensing image recognition. The state-of-the-art works exploit the deep convolutional neural networks (CNNs) for SAR ATR, leading to high computation costs. These deep CNN models are unsuitable to be deployed on resource-limited platforms. In this work, we propose a graph neural network (GNN) model to achieve accurate and low-latency SAR ATR. We transform the input SAR image into the graph representation. The proposed GNN model consists of a stack of GNN layers that operates on the input graph to perform target classification. Unlike the state-of-the-art CNNs, which need heavy convolution operations, the proposed GNN model has low computation complexity and achieves comparable high accuracy. The GNN-based approach enables our proposed \emph{input pruning} strategy. By filtering out the irrelevant vertices in the input graph, we can reduce the computation complexity. Moreover, we propose the \emph{model pruning} strategy to sparsify the model weight matrices which further reduces the computation complexity. We evaluate the proposed GNN model on the MSTAR dataset and ship discrimination dataset. The evaluation results show that the proposed GNN model achieves 99.38\% and 99.7\% classification accuracy on the above two datasets, respectively. The proposed pruning strategies can prune 98.6\% input vertices and 97\% weight entries with negligible accuracy loss. Compared with the state-of-the-art CNNs, the proposed GNN model has only 1/3000 computation cost and 1/80 model size.
Background: Convolutional Neural Networks can be effectively used only when data are endowed with an intrinsic concept of neighbourhood in the input space, as is the case of pixels in images. We introduce here Ph-CNN, a novel deep learning architecture for the classification of metagenomics data based on the Convolutional Neural Networks, with the patristic distance defined on the phylogenetic tree being used as the proximity measure. The patristic distance between variables is used together with a sparsified version of MultiDimensional Scaling to embed the phylogenetic tree in a Euclidean space. Results: Ph-CNN is tested with a domain adaptation approach on synthetic data and on a metagenomics collection of gut microbiota of 38 healthy subjects and 222 Inflammatory Bowel Disease patients, divided in 6 subclasses. Classification performance is promising when compared to classical algorithms like Support Vector Machines and Random Forest and a baseline fully connected neural network, e.g. the Multi-Layer Perceptron. Conclusion: Ph-CNN represents a novel deep learning approach for the classification of metagenomics data. Operatively, the algorithm has been implemented as a custom Keras layer taking care of passing to the following convolutional layer not only the data but also the ranked list of neighbourhood of each sample, thus mimicking the case of image data, transparently to the user. Keywords: Metagenomics; Deep learning; Convolutional Neural Networks; Phylogenetic trees
The automatic detection of critical findings in chest X-rays (CXR), such as pneumothorax, is important for assisting radiologists in their clinical workflow like triaging time-sensitive cases and screening for incidental findings. While deep learning (DL) models has become a promising predictive technology with near-human accuracy, they commonly suffer from a lack of explainability, which is an important aspect for clinical deployment of DL models in the highly regulated healthcare industry. For example, localizing critical findings in an image is useful for explaining the predictions of DL classification algorithms. While there have been a host of joint classification and localization methods for computer vision, the state-of-the-art DL models require locally annotated training data in the form of pixel level labels or bounding box coordinates. In the medical domain, this requires an expensive amount of manual annotation by medical experts for each critical finding. This requirement becomes a major barrier for training models that can rapidly scale to various findings. In this work, we address these shortcomings with an interpretable DL algorithm based on multi-instance learning that jointly classifies and localizes critical findings in CXR without the need for local annotations. We show competitive classification results on three different critical findings (pneumothorax, pneumonia, and pulmonary edema) from three different CXR datasets.
In recent years, spiking neural networks (SNNs) emerge as an alternative to deep neural networks (DNNs). SNNs present a higher computational efficiency using low-power neuromorphic hardware and require less labeled data for training using local and unsupervised learning rules such as spike timing-dependent plasticity (STDP). SNN have proven their effectiveness in image classification on simple datasets such as MNIST. However, to process natural images, a pre-processing step is required. Difference-of-Gaussians (DoG) filtering is typically used together with on-center/off-center coding, but it results in a loss of information that is detrimental to the classification performance. In this paper, we propose to use whitening as a pre-processing step before learning features with STDP. Experiments on CIFAR-10 show that whitening allows STDP to learn visual features that are closer to the ones learned with standard neural networks, with a significantly increased classification performance as compared to DoG filtering. We also propose an approximation of whitening as convolution kernels that is computationally cheaper to learn and more suited to be implemented on neuromorphic hardware. Experiments on CIFAR-10 show that it performs similarly to regular whitening. Cross-dataset experiments on CIFAR-10 and STL-10 also show that it is fairly stable across datasets, making it possible to learn a single whitening transformation to process different datasets.
In the world, about 7 to 10 million elderly people are suffering from Parkinson's Disease (PD) disease. Parkinson's disease is a common neurological degenerative disease, and its clinical characteristics are Tremors, rigidity, bradykinesia, and decreased autonomy. Its clinical manifestations are very similar to Multiple System Atrophy (MSA) disorders. Studies have shown that patients with Parkinson's disease often reach an irreparable situation when diagnosed, so As Parkinson's disease can be distinguished from MSA disease and get an early diagnosis, people are constantly exploring new methods. With the advent of the era of big data, deep learning has made major breakthroughs in image recognition and classification. Therefore, this study proposes to use The deep learning method to realize the diagnosis of Parkinson's disease, multiple system atrophy, and healthy people. This data source is from Istanbul University Cerrahpasa Faculty of Medicine Hospital. The processing of the original magnetic resonance image (Magnetic Resonance Image, MRI) is guided by the doctor of Istanbul University Cerrahpasa Faculty of Medicine Hospital. The focus of this experiment is to improve the existing neural network so that it can obtain good results in medical image recognition and diagnosis. An improved algorithm was proposed based on the pathological characteristics of Parkinson's disease, and good experimental results were obtained by comparing indicators such as model loss and accuracy.
Deep convolutional neural networks (DCNNs) have recently demonstrated high-quality results in single-image super-resolution (SR). DCNNs often suffer from over-parametrization and large amounts of redundancy, which results in inefficient inference and high memory usage, preventing massive applications on mobile devices. As a way to significantly reduce model size and computation time, binarized neural network has only been shown to excel on semantic-level tasks such as image classification and recognition. However, little effort of network quantization has been spent on image enhancement tasks like SR, as network quantization is usually assumed to sacrifice pixel-level accuracy. In this work, we explore an network-binarization approach for SR tasks without sacrificing much reconstruction accuracy. To achieve this, we binarize the convolutional filters in only residual blocks, and adopt a learnable weight for each binary filter. We evaluate this idea on several state-of-the-art DCNN-based architectures, and show that binarized SR networks achieve comparable qualitative and quantitative results as their real-weight counterparts. Moreover, the proposed binarized strategy could help reduce model size by 80% when applying on SRResNet, and could potentially speed up inference by 5 times.
Diabetic Retinopathy (DR) is a leading cause of vision loss globally. Yet despite its prevalence, the majority of affected people lack access to the specialized ophthalmologists and equipment required for assessing their condition. This can lead to delays in the start of treatment, thereby lowering their chances for a successful outcome. Machine learning systems that automatically detect the disease in eye fundus images have been proposed as a means of facilitating access to DR severity estimates for patients in remote regions or even for complementing the human expert's diagnosis. In this paper, we propose a machine learning system for the detection of referable DR in fundus images that is based on the paradigm of multiple-instance learning. By extracting local information from image patches and combining it efficiently through an attention mechanism, our system is able to achieve high classification accuracy. Moreover, it can highlight potential image regions where DR manifests through its characteristic lesions. We evaluate our approach on publicly available retinal image datasets, in which it exhibits near state-of-the-art performance, while also producing interpretable visualizations of its predictions.
Among ubiquitous multimodal data in the real world, text is the modality generated by human, while image reflects the physical world honestly. In a visual understanding application, machines are expected to understand images like human. Inspired by this, we propose a novel self-supervised learning method, named Text-enhanced Visual Deep InfoMax (TVDIM), to learn better visual representations by fully utilizing the naturally-existing multimodal data. Our core idea of self-supervised learning is to maximize the mutual information between features extracted from multiple views of a shared context to a rational degree. Different from previous methods which only consider multiple views from a single modality, our work produces multiple views from different modalities, and jointly optimizes the mutual information for features pairs of intra-modality and inter-modality. Considering the information gap between inter-modality features pairs from data noise, we adopt a \emph{ranking-based} contrastive learning to optimize the mutual information. During evaluation, we directly use the pre-trained visual representations to complete various image classification tasks. Experimental results show that, TVDIM significantly outperforms previous visual self-supervised methods when processing the same set of images.
Residual networks (ResNets) have been utilized for various computer vision and image processing applications. The residual connection improves the training of the network with better gradient flow. A residual block consists of few convolutional layers having trainable parameters, which leads to overfitting. Moreover, the present residual networks are not able to utilize the high and low frequency information suitably, which also challenges the generalization capability of the network. In this paper, a frequency disentangled residual network (FDResNet) is proposed to tackle these issues. Specifically, FDResNet includes separate connections in the residual block for low and high frequency components, respectively. Basically, the proposed model disentangles the low and high frequency components to increase the generalization ability. Moreover, the computation of low and high frequency components using fixed filters further avoids the overfitting. The proposed model is tested on benchmark CIFAR10/100, Caltech and TinyImageNet datasets for image classification. The performance of the proposed model is also tested in image retrieval framework. It is noticed that the proposed model outperforms its counterpart residual model. The effect of kernel size and standard deviation is also evaluated. The impact of the frequency disentangling is also analyzed using saliency map.
Deep neural networks used in computer vision have been shown to exhibit many social biases such as gender bias. Vision Transformers (ViTs) have become increasingly popular in computer vision applications, outperforming Convolutional Neural Networks (CNNs) in many tasks such as image classification. However, given that research on mitigating bias in computer vision has primarily focused on CNNs, it is important to evaluate the effect of a different network architecture on the potential for bias amplification. In this paper we therefore introduce a novel metric to measure bias in architectures, Accuracy Difference. We examine bias amplification when models belonging to these two architectures are used as a part of large multimodal models, evaluating the different image encoders of Contrastive Language Image Pretraining which is an important model used in many generative models such as DALL-E and Stable Diffusion. Our experiments demonstrate that architecture can play a role in amplifying social biases due to the different techniques employed by the models for feature extraction and embedding as well as their different learning properties. This research found that ViTs amplified gender bias to a greater extent than CNNs
With the increasing adoption of metal additive manufacturing (AM), researchers and practitioners are turning to data-driven approaches to optimise printing conditions. Cross-sectional images of melt tracks provide valuable information for tuning process parameters, developing parameter scaling data, and identifying defects. Here we present an image segmentation neural network that automatically identifies and measures melt track dimensions from a cross-section image. We use a U-Net architecture to train on a data set of 62 pre-labelled images obtained from different labs, machines, and materials coupled with image augmentation. When neural network hyperparameters such as batch size and learning rate are properly tuned, the learned model shows an accuracy for classification of over 99% and an F1 score over 90%. The neural network exhibits robustness when tested on images captured by various users, printed on different machines, and acquired using different microscopes. A post-processing module extracts the height and width of the melt pool, and the wetting angles. We discuss opportunities to improve model performance and avenues for transfer learning, such as extension to other AM processes such as directed energy deposition.
Computer vision tasks typically involve describing what is present in an image (e.g. classification, detection, segmentation, and captioning). We study a visual common sense task that requires understanding what is not present. Specifically, given an image (e.g. of a living room) and name of an object ("cushion"), a vision system is asked to predict semantically-meaningful regions (masks or bounding boxes) in the image where that object could be placed or is likely be placed by humans (e.g. on the sofa). We call this task: Semantic Placement (SP) and believe that such common-sense visual understanding is critical for assitive robots (tidying a house), and AR devices (automatically rendering an object in the user's space). Studying the invisible is hard. Datasets for image description are typically constructed by curating relevant images and asking humans to annotate the contents of the image; neither of those two steps are straightforward for objects not present in the image. We overcome this challenge by operating in the opposite direction: we start with an image of an object in context from web, and then remove that object from the image via inpainting. This automated pipeline converts unstructured web data into a dataset comprising pairs of images with/without the object. Using this, we collect a novel dataset, with ${\sim}1.3$M images across $9$ object categories, and train a SP prediction model called CLIP-UNet. CLIP-UNet outperforms existing VLMs and baselines that combine semantic priors with object detectors on real-world and simulated images. In our user studies, we find that the SP masks predicted by CLIP-UNet are favored $43.7\%$ and $31.3\%$ times when comparing against the $4$ SP baselines on real and simulated images. In addition, we demonstrate leveraging SP mask predictions from CLIP-UNet enables downstream applications like building tidying robots in indoor environments.
How similar is the human mind to the sophisticated machine-learning systems that mirror its performance? Models of object categorization based on convolutional neural networks (CNNs) have achieved human-level benchmarks in assigning known labels to novel images. These advances promise to support transformative technologies such as autonomous vehicles and machine diagnosis; beyond this, they also serve as candidate models for the visual system itself -- not only in their output but perhaps even in their underlying mechanisms and principles. However, unlike human vision, CNNs can be "fooled" by adversarial examples -- carefully crafted images that appear as nonsense patterns to humans but are recognized as familiar objects by machines, or that appear as one object to humans and a different object to machines. This seemingly extreme divergence between human and machine classification challenges the promise of these new advances, both as applied image-recognition systems and also as models of the human mind. Surprisingly, however, little work has empirically investigated human classification of such adversarial stimuli: Does human and machine performance fundamentally diverge? Or could humans decipher such images and predict the machine's preferred labels? Here, we show that human and machine classification of adversarial stimuli are robustly related: In eight experiments on five prominent and diverse adversarial imagesets, human subjects reliably identified the machine's chosen label over relevant foils. This pattern persisted for images with strong antecedent identities, and even for images described as "totally unrecognizable to human eyes". We suggest that human intuition may be a more reliable guide to machine (mis)classification than has typically been imagined, and we explore the consequences of this result for minds and machines alike.
The interpretation of medical images is a challenging task, often complicated by the presence of artifacts, occlusions, limited contrast and more. Most notable is the case of chest radiography, where there is a high inter-rater variability in the detection and classification of abnormalities. This is largely due to inconclusive evidence in the data or subjective definitions of disease appearance. An additional example is the classification of anatomical views based on 2D Ultrasound images. Often, the anatomical context captured in a frame is not sufficient to recognize the underlying anatomy. Current machine learning solutions for these problems are typically limited to providing probabilistic predictions, relying on the capacity of underlying models to adapt to limited information and the high degree of label noise. In practice, however, this leads to overconfident systems with poor generalization on unseen data. To account for this, we propose a system that learns not only the probabilistic estimate for classification, but also an explicit uncertainty measure which captures the confidence of the system in the predicted output. We argue that this approach is essential to account for the inherent ambiguity characteristic of medical images from different radiologic exams including computed radiography, ultrasonography and magnetic resonance imaging. In our experiments we demonstrate that sample rejection based on the predicted uncertainty can significantly improve the ROC-AUC for various tasks, e.g., by 8% to 0.91 with an expected rejection rate of under 25% for the classification of different abnormalities in chest radiographs. In addition, we show that using uncertainty-driven bootstrapping to filter the training data, one can achieve a significant increase in robustness and accuracy.
Tensor (multidimensional array) classification problem has become very popular in modern applications such as image recognition and high dimensional spatio-temporal data analysis. Support Tensor Machine (STM) classifier, which is extended from the support vector machine, takes CANDECOMP / Parafac (CP) form of tensor data as input and predicts the data labels. The distribution-free and statistically consistent properties of STM highlight its potential in successfully handling wide varieties of data applications. Training a STM can be computationally expensive with high-dimensional tensors. However, reducing the size of tensor with a random projection technique can reduce the computational time and cost, making it feasible to handle large size tensors on regular machines. We name an STM estimated with randomly projected tensor as Random Projection-based Support Tensor Machine (RPSTM). In this work, we propose a Tensor Ensemble Classifier (TEC), which aggregates multiple RPSTMs for big tensor classification. TEC utilizes the ensemble idea to minimize the excessive classification risk brought by random projection, providing statistically consistent predictions while taking the computational advantage of RPSTM. Since each RPSTM can be estimated independently, TEC can further take advantage of parallel computing techniques and be more computationally efficient. The theoretical and numerical results demonstrate the decent performance of TEC model in high-dimensional tensor classification problems. The model prediction is statistically consistent as its risk is shown to converge to the optimal Bayes risk. Besides, we highlight the trade-off between the computational cost and the prediction risk for TEC model. The method is validated by extensive simulation and a real data example. We prepare a python package for applying TEC, which is available at our GitHub.
This paper addresses the problem of 3D human pose estimation in the wild. A significant challenge is the lack of training data, i.e., 2D images of humans annotated with 3D poses. Such data is necessary to train state-of-the-art CNN architectures. Here, we propose a solution to generate a large set of photorealistic synthetic images of humans with 3D pose annotations. We introduce an image-based synthesis engine that artificially augments a dataset of real images with 2D human pose annotations using 3D motion capture data. Given a candidate 3D pose, our algorithm selects for each joint an image whose 2D pose locally matches the projected 3D pose. The selected images are then combined to generate a new synthetic image by stitching local image patches in a kinematically constrained manner. The resulting images are used to train an end-to-end CNN for full-body 3D pose estimation. We cluster the training data into a large number of pose classes and tackle pose estimation as a $K$-way classification problem. Such an approach is viable only with large training sets such as ours. Our method outperforms most of the published works in terms of 3D pose estimation in controlled environments (Human3.6M) and shows promising results for real-world images (LSP). This demonstrates that CNNs trained on artificial images generalize well to real images. Compared to data generated from more classical rendering engines, our synthetic images do not require any domain adaptation or fine-tuning stage.
Traditional change detection methods usually follow the image differencing, change feature extraction and classification framework, and their performance is limited by such simple image domain differencing and also the hand-crafted features. Recently, the success of deep convolutional neural networks (CNNs) has widely spread across the whole field of computer vision for their powerful representation abilities. In this paper, we therefore address the remote sensing image change detection problem with deep learning techniques. We firstly propose an end-to-end dual-branch architecture, termed as the W-Net, with each branch taking as input one of the two bi-temporal images as in the traditional change detection models. In this way, CNN features with more powerful representative abilities can be obtained to boost the final detection performance. Also, W-Net performs differencing in the feature domain rather than in the traditional image domain, which greatly alleviates loss of useful information for determining the changes. Furthermore, by reformulating change detection as an image translation problem, we apply the recently popular Generative Adversarial Network (GAN) in which our W-Net serves as the Generator, leading to a new GAN architecture for change detection which we call CDGAN. To train our networks and also facilitate future research, we construct a large scale dataset by collecting images from Google Earth and provide carefully manually annotated ground truths. Experiments show that our proposed methods can provide fine-grained change detection results superior to the existing state-of-the-art baselines.
Whole-Slide Imaging allows for the capturing and digitization of high-resolution images of histological specimen. An automated analysis of such images using deep learning models is therefore of high demand. The transformer architecture has been proposed as a possible candidate for effectively leveraging the high-resolution information. Here, the whole-slide image is partitioned into smaller image patches and feature tokens are extracted from these image patches. However, while the conventional transformer allows for a simultaneous processing of a large set of input tokens, the computational demand scales quadratically with the number of input tokens and thus quadratically with the number of image patches. To address this problem we propose a novel cascaded cross-attention network (CCAN) based on the cross-attention mechanism that scales linearly with the number of extracted patches. Our experiments demonstrate that this architecture is at least on-par with and even outperforms other attention-based state-of-the-art methods on two public datasets: On the use-case of lung cancer (TCGA NSCLC) our model reaches a mean area under the receiver operating characteristic (AUC) of 0.970 $\pm$ 0.008 and on renal cancer (TCGA RCC) reaches a mean AUC of 0.985 $\pm$ 0.004. Furthermore, we show that our proposed model is efficient in low-data regimes, making it a promising approach for analyzing whole-slide images in resource-limited settings. To foster research in this direction, we make our code publicly available on GitHub: XXX.
We present a domain adaption framework to address a domain mismatch between synthetic training and real-world testing data. We demonstrate our method on a challenging fine-grain classification problem: recognizing a font style from an image of text. In this task, it is very easy to generate lots of rendered font examples but very hard to obtain real-world labeled images. This real-to-synthetic domain gap caused poor generalization to new real data in previous font recognition methods (Chen et al. (2014)). In this paper, we introduce a Convolutional Neural Network decomposition approach, leveraging a large training corpus of synthetic data to obtain effective features for classification. This is done using an adaptation technique based on a Stacked Convolutional Auto-Encoder that exploits a large collection of unlabeled real-world text images combined with synthetic data preprocessed in a specific way. The proposed DeepFont method achieves an accuracy of higher than 80% (top-5) on a new large labeled real-world dataset we collected.
Most recent approaches for action recognition from video leverage deep architectures to encode the video clip into a fixed length representation vector that is then used for classification. For this to be successful, the network must be capable of suppressing irrelevant scene background and extract the representation from the most discriminative part of the video. Our contribution builds on the observation that spatio-temporal patterns characterizing actions in videos are highly correlated with objects and their location in the video. We propose Top-down Attention Action VLAD (TA-VLAD), a deep recurrent architecture with built-in spatial attention that performs temporally aggregated VLAD encoding for action recognition from videos. We adopt a top-down approach of attention, by using class specific activation maps obtained from a deep CNN pre-trained for image classification, to weight appearance features before encoding them into a fixed-length video descriptor using Gated Recurrent Units. Our method achieves state of the art recognition accuracy on HMDB51 and UCF101 benchmarks.