Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition

利用卷积网络中的线性结构实现高效评估

Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation

提出利用卷积滤波器线性结构加速大型卷积网络测试评估，实现CPU和GPU上卷积层2倍加速，精度损失在1%以内。

Convolutional neural networks with low-rank regularization

Large CNNs have delivered impressive performance in various computer vision applications. But the storage and computation requirements make it problematic for deploying these models on mobile devices. Recently, tensor decompositions have been used for speeding up CNNs. In this paper, we further develop the tensor decomposition technique. We propose a new algorithm for computing the low-rank tensor decomposition for removing the redundancy in the convolution kernels. The algorithm finds the exact global optimizer of the decomposition and is more effective than iterative methods. Based on the de…

AutoTune: Automatically Tuning Convolutional Neural Networks for Improved Transfer Learning

Transfer learning enables solving a specific task having limited data by using the pre-trained deep networks trained on large-scale datasets. Typically, while transferring the learned knowledge from source task to the target task, the last few layers are fine-tuned (re-trained) over the target dataset. However, these layers are originally designed for the source task that might not be suitable for the target task. In this paper, we introduce a mechanism for automatically tuning the Convolutional Neural Networks (CNN) for improved transfer learning. The pre-trained CNN layers are tuned with the…

Classifying cooking object's state using a tuned VGG convolutional neural network

In robotics, knowing the object states and recognizing the desired states are very important. Objects at different states would require different grasping. To achieve different states, different manipulations would be required, as well as different grasping. To analyze the objects at different states, a dataset of cooking objects was created. Cooking consists of various cutting techniques needed for different dishes (e.g. diced, julienne etc.). Identifying each of this state of cooking objects by the human can be difficult sometimes too. In this paper, we have analyzed seven different cooking …

Skin Lesion Classification Using Deep Multi-scale Convolutional Neural Networks

We present a deep learning approach to the ISIC 2017 Skin Lesion Classification Challenge using a multi-scale convolutional neural network. Our approach utilizes an Inception-v3 network pre-trained on the ImageNet dataset, which is fine-tuned for skin lesion classification using two different scales of input images.

Pollen Grain Microscopic Image Classification Using an Ensemble of Fine-Tuned Deep Convolutional Neural Networks

Pollen grain micrograph classification has multiple applications in medicine and biology. Automatic pollen grain image classification can alleviate the problems of manual categorisation such as subjectivity and time constraints. While a number of computer-based methods have been introduced in the literature to perform this task, classification performance needs to be improved for these methods to be useful in practice. In this paper, we present an ensemble approach for pollen grain microscopic image classification into four categories: Corylus Avellana well-developed pollen grain, Corylus Avel…

PCONet: A Convolutional Neural Network Architecture to Detect Polycystic Ovary Syndrome (PCOS) from Ovarian Ultrasound Images

Polycystic Ovary Syndrome (PCOS) is an endrocrinological dysfunction prevalent among women of reproductive age. PCOS is a combination of syndromes caused by an excess of androgens - a group of sex hormones - in women. Syndromes including acne, alopecia, hirsutism, hyperandrogenaemia, oligo-ovulation, etc. are caused by PCOS. It is also a major cause of female infertility. An estimated 15% of reproductive-aged women are affected by PCOS globally. The necessity of detecting PCOS early due to the severity of its deleterious effects cannot be overstated. In this paper, we have developed PCONet - a…

Gossip training for deep learning

We address the issue of speeding up the training of convolutional networks. Here we study a distributed method adapted to stochastic gradient descent (SGD). The parallel optimization setup uses several threads, each applying individual gradient descents on a local variable. We propose a new way to share information between different threads inspired by gossip algorithms and showing good consensus convergence properties. Our method called GoSGD has the advantage to be fully asynchronous and decentralized. We compared our method to the recent EASGD in \cite{elastic} on CIFAR-10 show encouraging …

Targeted Kernel Networks: Faster Convolutions with Attentive Regularization

We propose Attentive Regularization (AR), a method to constrain the activation maps of kernels in Convolutional Neural Networks (CNNs) to specific regions of interest (ROIs). Each kernel learns a location of specialization along with its weights through standard backpropagation. A differentiable attention mechanism requiring no additional supervision is used to optimize the ROIs. Traditional CNNs of different types and structures can be modified with this idea into equivalent Targeted Kernel Networks (TKNs), while keeping the network size nearly identical. By restricting kernel ROIs, we reduce…

Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?

Training a deep convolutional neural network (CNN) from scratch is difficult because it requires a large amount of labeled training data and a great deal of expertise to ensure proper convergence. A promising alternative is to fine-tune a CNN that has been pre-trained using, for instance, a large set of labeled natural images. However, the substantial differences between natural and medical images may advise against such knowledge transfer. In this paper, we seek to answer the following central question in the context of medical image analysis: \emph{Can the use of pre-trained deep CNNs with s…

Deep convolutional neural network application on rooftop detection for aerial image

As one of the most destructive disasters in the world, earthquake causes death, injuries, destruction and enormous damage to the affected area. It is significant to detect buildings after an earthquake in response to reconstruction and damage evaluation. In this research, we proposed an automatic rooftop detection method based on the convolutional neural network (CNN) to extract buildings in the city of Christchurch and tuned hyperparameters to detect small detached houses from the aerial image. The experiment result shows that our approach can effectively and accurately detect and segment bui…

Heterogeneous Multi-task Learning for Human Pose Estimation with Deep Convolutional Neural Network

We propose an heterogeneous multi-task learning framework for human pose estimation from monocular image with deep convolutional neural network. In particular, we simultaneously learn a pose-joint regressor and a sliding-window body-part detector in a deep network architecture. We show that including the body-part detection task helps to regularize the network, directing it to converge to a good solution. We report competitive and state-of-art results on several data sets. We also empirically show that the learned neurons in the middle layer of our network are tuned to localized body parts.

Driver Drowsiness Detection Model Using Convolutional Neural Networks Techniques for Android Application

A sleepy driver is arguably much more dangerous on the road than the one who is speeding as he is a victim of microsleeps. Automotive researchers and manufacturers are trying to curb this problem with several technological solutions that will avert such a crisis. This article focuses on the detection of such micro sleep and drowsiness using neural network based methodologies. Our previous work in this field involved using machine learning with multi-layer perceptron to detect the same. In this paper, accuracy was increased by utilizing facial landmarks which are detected by the camera and that…

Interpretable and Fine-Grained Visual Explanations for Convolutional Neural Networks

To verify and validate networks, it is essential to gain insight into their decisions, limitations as well as possible shortcomings of training data. In this work, we propose a post-hoc, optimization based visual explanation method, which highlights the evidence in the input image for a specific prediction. Our approach is based on a novel technique to defend against adversarial evidence (i.e. faulty evidence due to artefacts) by filtering gradients during optimization. The defense does not depend on human-tuned parameters. It enables explanations which are both fine-grained and preserve the c…

Land Use Classification in Remote Sensing Images by Convolutional Neural Networks

We explore the use of convolutional neural networks for the semantic classification of remote sensing scenes. Two recently proposed architectures, CaffeNet and GoogLeNet, are adopted, with three different learning modalities. Besides conventional training from scratch, we resort to pre-trained networks that are only fine-tuned on the target data, so as to avoid overfitting problems and reduce design time. Experiments on two remote sensing datasets, with markedly different characteristics, testify on the effectiveness and wide applicability of the proposed solution, which guarantees a significa…

Unconstrained Iris Segmentation using Convolutional Neural Networks

The extraction of consistent and identifiable features from an image of the human iris is known as iris recognition. Identifying which pixels belong to the iris, known as segmentation, is the first stage of iris recognition. Errors in segmentation propagate to later stages. Current segmentation approaches are tuned to specific environments. We propose using a convolution neural network for iris segmentation. Our algorithm is accurate when trained in a single environment and tested in multiple environments. Our network builds on the Mask R-CNN framework (He et al., ICCV 2017). Our approach segm…

Continuous Emotion Recognition with Spatiotemporal Convolutional Neural Networks

Facial expressions are one of the most powerful ways for depicting specific patterns in human behavior and describing human emotional state. Despite the impressive advances of affective computing over the last decade, automatic video-based systems for facial expression recognition still cannot handle properly variations in facial expression among individuals as well as cross-cultural and demographic aspects. Nevertheless, recognizing facial expressions is a difficult task even for humans. In this paper, we investigate the suitability of state-of-the-art deep learning architectures based on con…

Photoacoustic Microscopy with Sparse Data Enabled by Convolutional Neural Networks for Fast Imaging

Photoacoustic microscopy (PAM) has been a promising biomedical imaging technology in recent years. However, the point-by-point scanning mechanism results in low-speed imaging, which limits the application of PAM. Reducing sampling density can naturally shorten image acquisition time, which is at the cost of image quality. In this work, we propose a method using convolutional neural networks (CNNs) to improve the quality of sparse PAM images, thereby speeding up image acquisition while keeping good image quality. The CNN model utilizes both squeeze-and-excitation blocks and residual blocks to a…

M2CAI Workflow Challenge: Convolutional Neural Networks with Time Smoothing and Hidden Markov Model for Video Frames Classification

Our approach is among the three best to tackle the M2CAI Workflow challenge. The latter consists in recognizing the operation phase for each frames of endoscopic videos. In this technical report, we compare several classification models and temporal smoothing methods. Our submitted solution is a fine tuned Residual Network-200 on 80% of the training set with temporal smoothing using simple temporal averaging of the predictions and a Hidden Markov Model modeling the sequence.

Ensemble Learning using Transformers and Convolutional Networks for Masked Face Recognition

Wearing a face mask is one of the adjustments we had to follow to reduce the spread of the coronavirus. Having our faces covered by masks constantly has driven the need to understand and investigate how this behavior affects the recognition capability of face recognition systems. Current face recognition systems have extremely high accuracy when dealing with unconstrained general face recognition cases but do not generalize well with occluded masked faces. In this work, we propose a system for masked face recognition. The proposed system comprises two Convolutional Neural Network (CNN) models …

面向南亚洪灾频发国家的基于微调注意力架构的航拍洪灾场景分类

Aerial Flood Scene Classification Using Fine-Tuned Attention-based Architecture for Flood-Prone Countries in South Asia

本研究构建南亚洪灾航拍图像数据集，提出微调CCT分类方法并对比多种Transformer、CNN及YOLOv8模型，为南亚洪灾场景分类与搜救提供技术支撑。

针对MRI脑肿瘤图像分类与分割的微调卷积神经网络与大语言模型的比较与评估

A Comparison and Evaluation of Fine-tuned Convolutional Neural Networks to Large Language Models for Image Classification and Segmentation of Brain Tumors on MRI

本研究对比了微调前后的LLMs与CNNs在MRI脑肿瘤分类和分割任务中的表现，发现CNNs在准确率和空间定位上均优于LLMs，表明当前LLMs尚不适合直接处理此类医学图像任务。

Multi-label Object Attribute Classification using a Convolutional Neural Network

Objects of different classes can be described using a limited number of attributes such as color, shape, pattern, and texture. Learning to detect object attributes instead of only detecting objects can be helpful in dealing with a priori unknown objects. With this inspiration, a deep convolutional neural network for low-level object attribute classification, called the Deep Attribute Network (DAN), is proposed. Since object features are implicitly learned by object recognition networks, one such existing network is modified and fine-tuned for developing DAN. The performance of DAN is evaluated…

Glaucoma Detection From Raw Circumapillary OCT Images Using Fully Convolutional Neural Networks

Nowadays, glaucoma is the leading cause of blindness worldwide. We propose in this paper two different deep-learning-based approaches to address glaucoma detection just from raw circumpapillary OCT images. The first one is based on the development of convolutional neural networks (CNNs) trained from scratch. The second one lies in fine-tuning some of the most common state-of-the-art CNNs architectures. The experiments were performed on a private database composed of 93 glaucomatous and 156 normal B-scans around the optic nerve head of the retina, which were diagnosed by expert ophthalmologists…

Active, Continual Fine Tuning of Convolutional Neural Networks for Reducing Annotation Efforts

The splendid success of convolutional neural networks (CNNs) in computer vision is largely attributable to the availability of massive annotated datasets, such as ImageNet and Places. However, in medical imaging, it is challenging to create such large annotated datasets, as annotating medical images is not only tedious, laborious, and time consuming, but it also demands costly, specialty-oriented skills, which are not easily accessible. To dramatically reduce annotation cost, this paper presents a novel method to naturally integrate active learning and transfer learning (fine-tuning) into a si…

Δ-Patching：一种在不损失基础性能的情况下快速适配预训练卷积网络的框架

$Δ$-Patching: A Framework for Rapid Adaptation of Pre-trained Convolutional Networks without Base Performance Loss

本文提出Δ-Patching框架和轻量方法Δ-Networks，在不存储模型副本、仅训练少量参数的情况下高效微调预训练卷积网络，并在多种设置、架构及迁移学习、零样本域自适应、检测和分割等任务中验证其优于已有模型补丁方法。

License Plate Detection and Recognition Using Deeply Learned Convolutional Neural Networks

This work details Sighthounds fully automated license plate detection and recognition system. The core technology of the system is built using a sequence of deep Convolutional Neural Networks (CNNs) interlaced with accurate and efficient algorithms. The CNNs are trained and fine-tuned so that they are robust under different conditions (e.g. variations in pose, lighting, occlusion, etc.) and can work across a variety of license plate templates (e.g. sizes, backgrounds, fonts, etc). For quantitative analysis, we show that our system outperforms the leading license plate detection and recognition…

PocketNet：一种用于医学图像分析的更小神经网络

PocketNet: A Smaller Neural Network for Medical Image Analysis

针对医学影像深度学习模型庞大复杂、需专用硬件的问题，提出PocketNet范式，通过限制卷积网络通道数增长来减小模型规模，在保持分割和分类性能的同时大幅减少参数量、GPU内存和训练时间，使其能在资源受限环境中训练与部署。

Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches

We present a method for extracting depth information from a rectified image pair. Our approach focuses on the first stage of many stereo algorithms: the matching cost computation. We approach the problem by learning a similarity measure on small image patches using a convolutional neural network. Training is carried out in a supervised manner by constructing a binary classification data set with examples of similar and dissimilar pairs of patches. We examine two network architectures for this task: one tuned for speed, the other for accuracy. The output of the convolutional neural network is u…

Thanks for Nothing: Predicting Zero-Valued Activations with Lightweight Convolutional Neural Networks

Convolutional neural networks (CNNs) introduce state-of-the-art results for various tasks with the price of high computational demands. Inspired by the observation that spatial correlation exists in CNN output feature maps (ofms), we propose a method to dynamically predict whether ofm activations are zero-valued or not according to their neighboring activation values, thereby avoiding zero-valued activations and reducing the number of convolution operations. We implement the zero activation predictor (ZAP) with a lightweight CNN, which imposes negligible overheads and is easy to deploy on exis…

Homogeneous Vector Capsules Enable Adaptive Gradient Descent in Convolutional Neural Networks

Capsules are the name given by Geoffrey Hinton to vector-valued neurons. Neural networks traditionally produce a scalar value for an activated neuron. Capsules, on the other hand, produce a vector of values, which Hinton argues correspond to a single, composite feature wherein the values of the components of the vectors indicate properties of the feature such as transformation or contrast. We present a new way of parameterizing and training capsules that we refer to as homogeneous vector capsules (HVCs). We demonstrate, experimentally, that altering a convolutional neural network (CNN) to use …

Ensemble of Convolutional Neural Networks for Automatic Grading of Diabetic Retinopathy and Macular Edema

In this manuscript, we automate the procedure of grading of diabetic retinopathy and macular edema from fundus images using an ensemble of convolutional neural networks. The availability of limited amount of labeled data to perform supervised learning was circumvented by using transfer learning approach. The models in the ensemble were pre-trained on a large dataset comprising natural images and were later fine-tuned with the limited data for the task of choice. For an image, the ensemble of classifiers generate multiple predictions, and a max-voting based approach was utilized to attain the f…

Fully Convolutional Networks for Dense Semantic Labelling of High-Resolution Aerial Imagery

The trend towards higher resolution remote sensing imagery facilitates a transition from land-use classification to object-level scene understanding. Rather than relying purely on spectral content, appearance-based image features come into play. In this work, deep convolutional neural networks (CNNs) are applied to semantic labelling of high-resolution remote sensing data. Recent advances in fully convolutional networks (FCNs) are adapted to overhead data and shown to be as effective as in other domains. A full-resolution labelling is inferred using a deep FCN with no downsampling, obviating t…

Urban Change Detection by Fully Convolutional Siamese Concatenate Network with Attention

Change detection (CD) is an important problem in remote sensing, especially in disaster time for urban management. Most existing traditional methods for change detection are categorized based on pixel or objects. Object-based models are preferred to pixel-based methods for handling very high-resolution remote sensing (VHR RS) images. Such methods can benefit from the ongoing research on deep learning. In this paper, a fully automatic change-detection algorithm on VHR RS images is proposed that deploys Fully Convolutional Siamese Concatenate networks (FC-Siam-Conc). The proposed method uses pre…

An Experimental Study of the Impact of Pre-training on the Pruning of a Convolutional Neural Network

In recent years, deep neural networks have known a wide success in various application domains. However, they require important computational and memory resources, which severely hinders their deployment, notably on mobile devices or for real-time applications. Neural networks usually involve a large number of parameters, which correspond to the weights of the network. Such parameters, obtained with the help of a training process, are determinant for the performance of the network. However, they are also highly redundant. The pruning methods notably attempt to reduce the size of the parameter …

Webly Supervised Learning of Convolutional Networks

We present an approach to utilize large amounts of web data for learning CNNs. Specifically inspired by curriculum learning, we present a two-step approach for CNN training. First, we use easy images to train an initial visual representation. We then use this initial CNN and adapt it to harder, more realistic images by leveraging the structure of data and categories. We demonstrate that our two-stage CNN outperforms a fine-tuned CNN trained on ImageNet on Pascal VOC 2012. We also demonstrate the strength of webly supervised learning by localizing objects in web images and training a R-CNN styl…

Multiclass Burn Wound Image Classification Using Deep Convolutional Neural Networks

Millions of people are affected by acute and chronic wounds yearly across the world. Continuous wound monitoring is important for wound specialists to allow more accurate diagnosis and optimization of management protocols. Machine Learning-based classification approaches provide optimal care strategies resulting in more reliable outcomes, cost savings, healing time reduction, and improved patient satisfaction. In this study, we use a deep learning-based method to classify burn wound images into two or three different categories based on the wound conditions. A pre-trained deep convolutional ne…

Automatic Rank Selection for High-Speed Convolutional Neural Network

Low-rank decomposition plays a central role in accelerating convolutional neural network (CNN), and the rank of decomposed kernel-tensor is a key parameter that determines the complexity and accuracy of a neural network. In this paper, we define rank selection as a combinatorial optimization problem and propose a methodology to minimize network complexity while maintaining the desired accuracy. Combinatorial optimization is not feasible due to search space limitations. To restrict the search space and obtain the optimal rank, we define the space constraint parameters with a boundary condition.…

Adapting Convolutional Neural Networks for Geographical Domain Shift

We present the winning solution for the Inclusive Images Competition organized as part of the Conference on Neural Information Processing Systems (NeurIPS 2018) Competition Track. The competition was organized to study ways to cope with domain shift in image processing, specifically geographical shift: the training and two test sets in the competition had different geographical distributions. Our solution has proven to be relatively straightforward and simple: it is an ensemble of several CNNs where only the last layer is fine-tuned with the help of a small labeled set of tuning labels made av…

Towards Better Exploiting Convolutional Neural Networks for Remote Sensing Scene Classification

We present an analysis of three possible strategies for exploiting the power of existing convolutional neural networks (ConvNets) in different scenarios from the ones they were trained: full training, fine tuning, and using ConvNets as feature extractors. In many applications, especially including remote sensing, it is not feasible to fully design and train a new ConvNet, as this usually requires a considerable amount of labeled data and demands high computational costs. Therefore, it is important to understand how to obtain the best profit from existing ConvNets. We perform experiments with s…

Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruning

Deep convolutional neural networks (CNNs) are indispensable to state-of-the-art computer vision algorithms. However, they are still rarely deployed on battery-powered mobile devices, such as smartphones and wearable gadgets, where vision algorithms can enable many revolutionary real-world applications. The key limiting factor is the high energy consumption of CNN processing due to its high computational complexity. While there are many previous efforts that try to reduce the CNN model size or amount of computation, we find that they do not necessarily result in lower energy consumption, and th…

Fine-Pruning: Joint Fine-Tuning and Compression of a Convolutional Network with Bayesian Optimization

When approaching a novel visual recognition problem in a specialized image domain, a common strategy is to start with a pre-trained deep neural network and fine-tune it to the specialized domain. If the target domain covers a smaller visual space than the source domain used for pre-training (e.g. ImageNet), the fine-tuned network is likely to be over-parameterized. However, applying network pruning as a post-processing step to reduce the memory requirements has drawbacks: fine-tuning and pruning are performed independently; pruning parameters are set once and cannot adapt over time; and the hi…

2^B3^C: 2 Box 3 Crop of Facial Image for Gender Classification with Convolutional Networks

In this paper, we tackle the classification of gender in facial images with deep learning. Our convolutional neural networks (CNN) use the VGG-16 architecture [1] and are pretrained on ImageNet for image classification. Our proposed method (2^B3^C) first detects the face in the facial image, increases the margin of a detected face by 50%, cropping the face with two boxes three crop schemes (Left, Middle, and Right crop) and extracts the CNN predictions on the cropped schemes. The CNNs of our method is fine-tuned on the Adience and LFW with gender annotations. We show the effectiveness of our m…

Quantifying Radiographic Knee Osteoarthritis Severity using Deep Convolutional Neural Networks

This paper proposes a new approach to automatically quantify the severity of knee osteoarthritis (OA) from radiographs using deep convolutional neural networks (CNN). Clinically, knee OA severity is assessed using Kellgren \& Lawrence (KL) grades, a five point scale. Previous work on automatically predicting KL grades from radiograph images were based on training shallow classifiers using a variety of hand engineered features. We demonstrate that classification accuracy can be significantly improved using deep convolutional neural network models pre-trained on ImageNet and fine-tuned on knee O…

Analysis of Random Perturbations for Robust Convolutional Neural Networks

Recent work has extensively shown that randomized perturbations of neural networks can improve robustness to adversarial attacks. The literature is, however, lacking a detailed compare-and-contrast of the latest proposals to understand what classes of perturbations work, when they work, and why they work. We contribute a detailed evaluation that elucidates these questions and benchmarks perturbation based defenses consistently. In particular, we show five main results: (1) all input perturbation defenses, whether random or deterministic, are equivalent in their efficacy, (2) attacks transfer b…

Studying the Plasticity in Deep Convolutional Neural Networks using Random Pruning

Recently there has been a lot of work on pruning filters from deep convolutional neural networks (CNNs) with the intention of reducing computations.The key idea is to rank the filters based on a certain criterion (say, l1-norm) and retain only the top ranked filters. Once the low scoring filters are pruned away the remainder of the network is fine tuned and is shown to give performance comparable to the original unpruned network. In this work, we report experiments which suggest that the comparable performance of the pruned network is not due to the specific criterion chosen but due to the inh…

Fully Convolutional Recurrent Network for Handwritten Chinese Text Recognition

This paper proposes an end-to-end framework, namely fully convolutional recurrent network (FCRN) for handwritten Chinese text recognition (HCTR). Unlike traditional methods that rely heavily on segmentation, our FCRN is trained with online text data directly and learns to associate the pen-tip trajectory with a sequence of characters. FCRN consists of four parts: a path-signature layer to extract signature features from the input pen-tip trajectory, a fully convolutional network to learn informative representation, a sequence modeling layer to make per-frame predictions on the input sequence a…

Iris and periocular recognition in arabian race horses using deep convolutional neural networks

This paper presents a study devoted to recognizing horses by means of their iris and periocular features using deep convolutional neural networks (DCNNs). Identification of race horses is crucial for animal identity confirmation prior to racing. As this is usually done shortly before a race, fast and reliable methods that are friendly and inflict no harm upon animals are important. Iris recognition has been shown to work with horse irides, provided that algorithms deployed for such task are fine-tuned for horse irides and input data is of very high quality. In our work, we examine a possibilit…

Improving Electron Micrograph Signal-to-Noise with an Atrous Convolutional Encoder-Decoder

We present an atrous convolutional encoder-decoder trained to denoise 512$\times$512 crops from electron micrographs. It consists of a modified Xception backbone, atrous convoltional spatial pyramid pooling module and a multi-stage decoder. Our neural network was trained end-to-end to remove Poisson noise applied to low-dose ($\ll$ 300 counts ppx) micrographs created from a new dataset of 17267 2048$\times$2048 high-dose ($>$ 2500 counts ppx) micrographs and then fine-tuned for ordinary doses (200-2500 counts ppx). Its performance is benchmarked against bilateral, non-local means, total variat…

微调隐式函数的不确定性建模

Uncertainty modeling for fine-tuned implicit functions

针对隐式函数重建因输入稀疏、分布偏移导致的结果可靠性问题，提出新型不确定性估计方法Dropsembles，经实验验证其能以远低于深度集成的计算成本达到相当的准确率与校准水平。

Feeding Hand-Crafted Features for Enhancing the Performance of Convolutional Neural Networks

Since the convolutional neural network (CNN) is be- lieved to find right features for a given problem, the study of hand-crafted features is somewhat neglected these days. In this paper, we show that finding an appropriate feature for the given problem may be still important as they can en- hance the performance of CNN-based algorithms. Specif- ically, we show that feeding an appropriate feature to the CNN enhances its performance in some face related works such as age/gender estimation, face detection and emotion recognition. We use Gabor filter bank responses for these tasks, feeding them to…

A Deep Convolutional Neural Network for COVID-19 Detection Using Chest X-Rays

Purpose: We present image classifiers based on Dense Convolutional Networks and transfer learning to classify chest X-ray images according to three labels: COVID-19, pneumonia and normal. Methods: We fine-tuned neural networks pretrained on ImageNet and applied a twice transfer learning approach, using NIH ChestX-ray14 dataset as an intermediate step. We also suggested a novelty called output neuron keeping, which changes the twice transfer learning technique. In order to clarify the modus operandi of the models, we used Layer-wise Relevance Propagation (LRP) to generate heatmaps. Results: We …

Recovering from Random Pruning: On the Plasticity of Deep Convolutional Neural Networks

Recently there has been a lot of work on pruning filters from deep convolutional neural networks (CNNs) with the intention of reducing computations. The key idea is to rank the filters based on a certain criterion (say, $l_1$-norm, average percentage of zeros, etc) and retain only the top ranked filters. Once the low scoring filters are pruned away the remainder of the network is fine tuned and is shown to give performance comparable to the original unpruned network. In this work, we report experiments which suggest that the comparable performance of the pruned network is not due to the specif…

Online Adaptation of Convolutional Neural Networks for Video Object Segmentation

We tackle the task of semi-supervised video object segmentation, i.e. segmenting the pixels belonging to an object in the video using the ground truth pixel mask for the first frame. We build on the recently introduced one-shot video object segmentation (OSVOS) approach which uses a pretrained network and fine-tunes it on the first frame. While achieving impressive performance, at test time OSVOS uses the fine-tuned network in unchanged form and is not able to adapt to large changes in object appearance. To overcome this limitation, we propose Online Adaptive Video Object Segmentation (OnAVOS)…