Obesity is an important concern in public health, and Body Mass Index is one of the useful (and proliferant) measures. We use Convolutional Neural Networks to determine Body Mass Index from photographs in a study with 161 participants. Low data, a common problem in medicine, is addressed by reducing the information in the photographs by generating silhouette images. Results present with high correlation when tested on unseen data.
We make the following striking observation: fully convolutional VAE models trained on 32x32 ImageNet can generalize well, not just to 64x64 but also to far larger photographs, with no changes to the model. We use this property, applying fully convolutional models to lossless compression, demonstrating a method to scale the VAE-based 'Bits-Back with ANS' algorithm for lossless compression to large color photographs, and achieving state of the art for compression of full size ImageNet images. We release Craystack, an open source library for convenient prototyping of lossless compression using pr…
In this paper, a straightforward enhancement learning algorithm based on Separation Index (SI) concept is proposed for Convolutional Neural Networks (CNNs). At first, the SI as a supervised complexity measure is explained its usage in better learning of CNNs for classification problems illustrate. Then, a learning strategy proposes through which the first layer of a CNN is optimized by maximizing the SI, and the further layers are trained through the backpropagation algorithm to learn further layers. In order to maximize the SI at the first layer, A variant of ranking loss is optimized by usin…
University College London（伦敦大学学院）；The Alan Turing Institute（艾伦·图灵研究所）
People deploy top-down, goal-directed attention to accomplish tasks, such as finding lost keys. By tuning the visual system to relevant information sources, object recognition can become more efficient (a benefit) and more biased toward the target (a potential cost). Motivated by selective attention in categorisation models, we developed a goal-directed attention mechanism that can process naturalistic (photographic) stimuli. Our attention mechanism can be incorporated into any existing deep convolutional neural network (DCNNs). The processing stages in DCNNs have been related to ventral visua…
OPPO US Research Center（OPPO美国研究中心）；University of Wisconsin, Madison（威斯康星大学麦迪逊分校）；New York University（纽约大学）；Harvard University（哈佛大学）
The memory consumption of most Convolutional Neural Network (CNN) architectures grows rapidly with increasing depth of the network, which is a major constraint for efficient network training on modern GPUs with limited memory, embedded systems, and mobile devices. Several studies show that the feature maps (as generated after the convolutional layers) are the main bottleneck in this memory problem. Often, these feature maps mimic natural photographs in the sense that their energy is concentrated in the spectral domain. Although embedding CNN architectures in the spectral domain is widely explo…
Convolutional neural networks (CNNs) achieve state-of-the-art performance in a wide variety of tasks in computer vision. However, interpreting CNNs still remains a challenge. This is mainly due to the large number of parameters in these networks. Here, we investigate the role of compression and particularly pruning filters in the interpretation of CNNs. We exploit our recently-proposed greedy structural compression scheme that prunes filters in a trained CNN. In our compression, the filter importance index is defined as the classification accuracy reduction (CAR) of the network after pruning t…
Vision Transformers versus convolutional neural networks for fine-grained orchid genus identification in a species-rich, data-poor flora: a controlled benchmark on the Orchidaceae of New Guinea
James Cook University（詹姆斯库克大学）；Southwest Papua Natural Resources Conservation Agency, Ministry of Forestry, Indonesia（印度尼西亚林业部西南巴布亚自然资源保护局）；National Research and Innovation Agency (BRIN), Republic of Indonesia（印度尼西亚共和国国家研究与创新局（BRIN））；Royal Botanic Gardens, Kew（英国皇家植物园邱园）；Australian Tropical Herbarium（澳大利亚热带植物标本馆）；Commonwealth Industrial and Scientific Research Organisation (CSIRO)（澳大利亚联邦科学与工业研究组织（CSIRO））；Australian National Herbarium（澳大利亚国家植物标本馆）
Federal University of Technology - Parana（巴拉那联邦理工大学）；University of Münster（明斯特大学）
In this paper, we introduce an approach for detecting modifications in assembled printed circuit boards based on photographs taken without tight control over perspective and illumination conditions. One instance of this problem is the visual inspection of gas pumps PCBs, which can be modified by fraudsters wishing to deceive costumers or evade taxes. Given the uncontrolled environment and the huge number of possible modifications, we address the problem as a case of anomaly detection, proposing an approach that is directed towards the characteristics of that scenario, while being well-suited f…
We present an approach to accelerating a wide variety of image processing operators. Our approach uses a fully-convolutional network that is trained on input-output pairs that demonstrate the operator's action. After training, the original operator need not be run at all. The trained network operates at full resolution and runs in constant time. We investigate the effect of network architecture on approximation accuracy, runtime, and memory footprint, and identify a specific architecture that balances these considerations. We evaluate the presented approach on ten advanced image processing ope…
Modern digital cameras and smartphones mostly rely on image signal processing (ISP) pipelines to produce realistic colored RGB images. However, compared to DSLR cameras, low-quality images are usually obtained in many portable mobile devices with compact camera sensors due to their physical limitations. The low-quality images have multiple degradations i.e., sub-pixel shift due to camera motion, mosaick patterns due to camera color filter array, low-resolution due to smaller camera sensors, and the rest information are corrupted by the noise. Such degradations limit the performance of current …
Recent technological advances in synthetic data have enabled the generation of images with such high quality that human beings cannot tell the difference between real-life photographs and Artificial Intelligence (AI) generated images. Given the critical necessity of data reliability and authentication, this article proposes to enhance our ability to recognise AI-generated images through computer vision. Initially, a synthetic dataset is generated that mirrors the ten classes of the already available CIFAR-10 dataset with latent diffusion which provides a contrasting set of images for compariso…
University of Chinese Academy of Sciences（中国科学院大学）
A deep convolutional fuzzy system (DCFS) on a high-dimensional input space is a multi-layer connection of many low-dimensional fuzzy systems, where the input variables to the low-dimensional fuzzy systems are selected through a moving window across the input spaces of the layers. To design the DCFS based on input-output data pairs, we propose a bottom-up layer-by-layer scheme. Specifically, by viewing each of the first-layer fuzzy systems as a weak estimator of the output based only on a very small portion of the input variables, we design these fuzzy systems using the WM Method. After the fir…
University of Amsterdam（阿姆斯特丹大学）；Ecole Normale Supérieure（巴黎高等师范学院）
Deep neural network algorithms are difficult to analyze because they lack structure allowing to understand the properties of underlying transforms and invariants. Multiscale hierarchical convolutional networks are structured deep convolutional networks where layers are indexed by progressively higher dimensional attributes, which are learned from training data. Each new layer is computed with multidimensional convolutions along spatial and attribute variables. We introduce an efficient implementation of such networks where the dimensionality is progressively reduced by averaging intermediate l…
University of Bristol（布里斯托大学）；Centre for Modelling and Simulation（建模与仿真中心）
Prior work has shown Convolutional Neural Networks (CNNs) trained on surrogate Computer Aided Design (CAD) models are able to detect and classify real-world artefacts from photographs. The applications of which support twinning of digital and physical assets in design, including rapid extraction of part geometry from model repositories, information search \& retrieval and identifying components in the field for maintenance, repair, and recording. The performance of CNNs in classification tasks have been shown dependent on training data set size and number of classes. Where prior works have use…
Using Multiple Dermoscopic Photographs of One Lesion Improves Melanoma Classification via Deep Learning: A Prognostic Diagnostic Accuracy Study
German Cancer Research Center (DKFZ)（德国癌症研究中心）；University Medical Center Mannheim, Ruprecht-Karl University of Heidelberg（海德堡鲁普雷希特-卡尔大学曼海姆医学中心）；DKFZ Hector Cancer Institute at the University Medical Center Mannheim（曼海姆医学中心DKFZ赫克托癌症研究所）；University Hospital Carl Gustav Carus, Technische Universität Dresden（德累斯顿工业大学卡尔·古斯塔夫·卡鲁斯大学医院）；University Hospital (UKSH), Kiel（基尔大学医院（UKSH））
Deep learning with a convolutional neural network (CNN) has been proved to be very effective in feature extraction and representation of images. For image classification problems, this work aim at finding which classifier is more competitive based on high-level deep features of images. In this report, we have discussed the nearest neighbor, support vector machines and extreme learning machines for image classification under deep convolutional activation feature representation. Specifically, we adopt the benchmark object recognition dataset from multiple sources with domain bias for evaluating …
Prediction of future movement of stock prices has been a subject matter of many research work. In this work, we propose a hybrid approach for stock price prediction using machine learning and deep learning-based methods. We select the NIFTY 50 index values of the National Stock Exchange of India, over a period of four years, from January 2015 till December 2019. Based on the NIFTY data during the said period, we build various predictive models using machine learning approaches, and then use those models to predict the Close value of NIFTY 50 for the year 2019, with a forecast horizon of one we…
Due to the nature of deep learning approaches, it is inherently difficult to understand which aspects of a molecular graph drive the predictions of the network. As a mitigation strategy, we constrain certain weights in a multi-task graph convolutional neural network according to the Gini index to maximize the "inequality" of the learned representations. We show that this constraint does not degrade evaluation metrics for some targets, and allows us to combine the outputs of the graph convolutional operation in a visually interpretable way. We then perform a proof-of-concept experiment on quant…
HHMI Janelia Research Campus（霍华德·休斯医学研究所珍利亚研究园区）；Wuhan National Laboratory for Optoelectronics, HUST（华中科技大学武汉国家光电研究中心）；Institut de la Vision, Sorbonne Université, CNRS（索邦大学法国国家科学研究中心视觉研究所）；Harvard University（哈佛大学）；Stanford University（斯坦福大学）
Differentiable simulations of optical systems can be combined with deep learning-based reconstruction networks to enable high performance computational imaging via end-to-end (E2E) optimization of both the optical encoder and the deep decoder. This has enabled imaging applications such as 3D localization microscopy, depth estimation, and lensless photography via the optimization of local optical encoders. More challenging computational imaging applications, such as 3D snapshot microscopy which compresses 3D volumes into single 2D images, require a highly non-local optical encoder. We show that…
Image denoising is an essential tool in computational photography. Standard denoising techniques, which use deep neural networks at their core, require pairs of clean and noisy images for its training. If we do not possess the clean samples, we can use blind-spot neural network architectures, which estimate the pixel value based on the neighbouring pixels only. These networks thus allow training on noisy images directly, as they by-design avoid trivial solutions. Nowadays, the blind-spot is mostly achieved using shifted convolutions or serialization. We propose a novel fully convolutional netw…
For several skin conditions such as vitiligo, accurate segmentation of lesions from skin images is the primary measure of disease progression and severity. Existing methods for vitiligo lesion segmentation require manual intervention. Unfortunately, manual segmentation is time and labor-intensive, as well as irreproducible between physicians. We introduce a convolutional neural network (CNN) that quickly and robustly performs vitiligo skin lesion segmentation. Our CNN has a U-Net architecture with a modified contracting path. We use the CNN to generate an initial segmentation of the lesion, th…
Imperial College London（帝国理工学院）；Hellebore Capital Limited（Hellebore Capital有限公司）；Ecole Polytechnique（巴黎综合理工学院）
We propose Significance-Offset Convolutional Neural Network, a deep convolutional network architecture for regression of multivariate asynchronous time series. The model is inspired by standard autoregressive (AR) models and gating mechanisms used in recurrent neural networks. It involves an AR-like weighting system, where the final predictor is obtained as a weighted sum of adjusted regressors, while the weights are datadependent functions learnt through a convolutional network. The architecture was designed for applications on asynchronous time series and is evaluated on such datasets: a hed…
Indira Gandhi Delhi Technical University for Women（英迪拉·甘地德里女子技术大学）
As humans, we can remember certain visuals in great detail, and sometimes even after viewing them once. What is even more interesting is that humans tend to remember and forget the same things, suggesting that there might be some general internal characteristics of an image to encode and discard similar types of information. Research suggests that some pictures tend to be memorized more than others. The ability of an image to be remembered by different viewers is one of its intrinsic properties. In visualization and photography, creating memorable images is a difficult task. Hence, to solve th…
Government Technology Agency of Singapore（新加坡政府科技局）；Temple University（天普大学）；Senseable City Lab（可感知城市实验室）
Urban canopy cover is important to mitigate the impact of climate change. Yet, existing quantification of urban greenery is either manual and not scalable, or use traditional computer vision methods that are inaccurate. We train deep convolutional neural networks (DCNNs) on datasets used for self-driving cars to estimate urban greenery instead, and find that our semantic segmentation and direct end-to-end estimation method are more accurate and scalable, reducing mean absolute error of estimating the Green View Index (GVI) metric from 10.1% to 4.67%. With the revised DCNN methods, the Treepedi…
Arbitrary style transfer is the task of synthesis of an image that has never been seen before, using two given images: content image and style image. The content image forms the structure, the basic geometric lines and shapes of the resulting image, while the style image sets the color and texture of the result. The word "arbitrary" in this context means the absence of any one pre-learned style. So, for example, convolutional neural networks capable of transferring a new style only after training or retraining on a new amount of data are not con-sidered to solve such a problem, while networks …
University of Saskatchewan（萨斯喀彻温大学）；University of Stanford（斯坦福大学）
Colorectal cancer is the third most common cancer-related death after lung cancer and breast cancer worldwide. The risk of developing colorectal cancer could be reduced by early diagnosis of polyps during a colonoscopy. Computer-aided diagnosis systems have the potential to be applied for polyp screening and reduce the number of missing polyps. In this paper, we compare the performance of different deep learning architectures as feature extractors, i.e. ResNet, DenseNet, InceptionV3, InceptionResNetV2 and SE-ResNeXt in the encoder part of a U-Net architecture. We validated the performance of p…
CITIC Universidade da Coruña（拉科鲁尼亚大学CITIC）；Sleep Center & Clinical Neurophysiology Haaglanden Medisch Centrum（海牙兰登医疗中心睡眠中心与临床神经生理学）
Sleep stages classification is a crucial task in the context of sleep studies. It involves the simultaneous analysis of multiple signals recorded during sleep. However, it is complex and tedious, and even the trained expert can spend several hours scoring a single night recording. Multiple automatic methods have tried to solve these problems in the past, most of them by classifying a feature vector that is engineered for a specific dataset. In this work, we avoid this bias using a deep learning model that learns relevant features without human intervention. Particularly, we propose an ensemble…
University of Houston（休斯顿大学）；Oak Ridge Associated Universities（橡树岭联合大学）
Satellite-derived measurements are negatively impacted by cloud cover and surface reflectivity. These biases must be discarded and significantly increase the amount of missing data within remote sensing images. This paper expands the application of a partial convolutional neural network (PCNN) to incorporate depthwise convolution layers, conferring temporal dimensionality to the imputation process. The addition of a temporal dimension to the imputation process adds a state of successive existence within the dataset which spatial imputation cannot capture. The depthwise convolution process enab…
Indian Institute of Technology (Indian School of Mines), Dhanbad（印度理工学院（印度矿业学院），丹巴德）；University of Tartu（塔尔图大学）
Scientific publications play a vital role in the career of a researcher. However, some articles become more popular than others among the research community and subsequently drive future research directions. One of the indicative signs of popular articles is the number of citations an article receives. The citation count, which is also the basis with various other metrics, such as the journal impact factor score, the $h$-index, is an essential measure for assessing a scientific paper's quality. In this work, we proposed a Graph Convolutional Network (GCN) based framework for estimating future …
