Retrieval networks are essential for searching and indexing. Compared to classification networks, attention visualization for retrieval networks is hardly studied. We formulate attention visualization as a constrained optimization problem. We leverage the unit L2-Norm constraint as an attention filter (L2-CAF) to localize attention in both classification and retrieval networks. Unlike recent literature, our approach requires neither architectural changes nor fine-tuning. Thus, a pre-trained network's performance is never undermined
L2-CAF is quantitatively evaluated using weakly supervised object localization. State-of-the-art results are achieved on classification networks. For retrieval networks, significant improvement margins are achieved over a Grad-CAM baseline. Qualitative evaluation demonstrates how the L2-CAF visualizes attention per frame for a recurrent retrieval network. Further ablation studies highlight the computational cost of our approach and compare L2-CAF with other feasible alternatives. Code available at https://bit.ly/3iDBLFv
George Mason University（乔治梅森大学）；Clarkson University（克拉克森大学）
Nowadays, the Convolutional Neural Networks (CNNs) have achieved impressive performance on many computer vision related tasks, such as object detection, image recognition, image retrieval, etc. These achievements benefit from the CNNs outstanding capability to learn the input features with deep layers of neuron structures and iterative training process. However, these learned features are hard to identify and interpret from a human vision perspective, causing a lack of understanding of the CNNs internal working mechanism. To improve the CNN interpretability, the CNN visualization is well utili…
Feature Visualization in 3D Convolutional Neural Networks
College of Biological Sciences, China Agricultural University, Beijing, 100193, China（中国农业大学生命科学学院）；Beijing Institute for Brain Research, Chinese Academy of Medical Sciences, Peking Union Medical College, Beijing, 102206, China（北京脑科学研究院）；Chinese Institute for Brain Research, Beijing 102206, China（中国脑科学研究院）
Recently, convolutional neural networks (CNNs) have shown great success on the task of monocular depth estimation. A fundamental yet unanswered question is: how CNNs can infer depth from a single image. Toward answering this question, we consider visualization of inference of a CNN by identifying relevant pixels of an input image to depth estimation. We formulate it as an optimization problem of identifying the smallest number of image pixels from which the CNN can estimate a depth map with the minimum difference from the estimate from the entire image. To cope with a difficulty with optimizat…
Charité – Universitätsmedizin Berlin（柏林夏里特医学院）；Freie Universität Berlin（柏林自由大学）；Humboldt-Universität zu Berlin（柏林洪堡大学）；Berlin Institute of Health（柏林健康研究所）；Bernstein Center for Computational Neuroscience（伯恩斯坦计算神经科学中心）
A major prerequisite for the application of machine learning models in clinical decision making is trust and interpretability. Current explainability studies in the neuroimaging community have mostly focused on explaining individual decisions of trained models, e.g. obtained by a convolutional neural network (CNN). Using attribution methods such as layer-wise relevance propagation or SHAP heatmaps can be created that highlight which regions of an input are more relevant for the decision than others. While this allows the detection of potential data set biases and can be used as a guide for a h…
In this paper we introduce a tool called Principal Image Sections Mapping - PRISM, dedicated for PyTorch, but can be easily ported to other deep learning frameworks. Presented software relies on Principal Component Analysis to visualize the most significant features recognized by a given Convolutional Neural Network. Moreover, it allows to display comparative set features between images processed in the same batch, therefore PRISM can be a method well synerging with technique Explanation by Example.
Given the progress in image recognition with recent data driven paradigms, it's still expensive to manually label a large training data to fit a convolutional neural network (CNN) model. This paper proposes a hybrid supervised-unsupervised method combining a pre-trained AlexNet with Latent Dirichlet Allocation (LDA) to extract image topics from both an unlabeled life-logging dataset and the COCO dataset. We generate the bag-of-words representations of an egocentric dataset from the softmax layer of AlexNet and use LDA to visualize the subject's living genre with duplicated images. We use a sub…
We test this premise and explore representation spaces from a single deep convolutional network and their visualization to argue for a novel unified feature extraction framework. The objective is to utilize and re-purpose trained feature extractors without the need for network retraining on three remote sensing tasks i.e. superpixel mapping, pixel-level segmentation and semantic based image visualization. By leveraging the same convolutional feature extractors and viewing them as visual information extractors that encode different image representation spaces, we demonstrate a preliminary induc…
Institute of Visual and Analytic Computing（视觉与分析计算研究所）
Convolutional neural networks (CNN) have become a powerful tool for detecting patterns in image data. Recent papers report promising results in the domain of disease detection using brain MRI data. Despite the high accuracy obtained from CNN models for MRI data so far, almost no papers provided information on the features or image regions driving this accuracy as adequate methods were missing or challenging to apply. Recently, the toolbox iNNvestigate has become available, implementing various state of the art methods for deep learning visualizations. Currently, there is a great demand for a c…
University of Southern California（南加州大学）；US Army Research Laboratory（美国陆军研究实验室）
In this work, we study the power of Saak features as an effort towards interpretable deep learning. Being inspired by the operations of convolutional layers of convolutional neural networks, multi-stage Saak transform was proposed. Based on this foundation, we provide an in-depth examination on Saak features, which are coefficients of the Saak transform, by analyzing their properties through visualization and demonstrating their applications in image classification. Being similar to CNN features, Saak features at later stages have larger receptive fields, yet they are obtained in a one-pass fe…
University of New Mexico（新墨西哥大学）；Kent State University（肯特州立大学）；US Army Research Laboratory（美国陆军研究实验室）；Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）
Convolutional Neural Networks(CNNs) are complex systems. They are trained so they can adapt their internal connections to recognize images, texts and more. It is both interesting and helpful to visualize the dynamics within such deep artificial neural networks so that people can understand how these artificial networks are learning and making predictions. In the field of scientific simulations, visualization tools like Paraview have long been utilized to provide insights and understandings. We present in situ TensorView to visualize the training and functioning of CNNs as if they are systems o…
Gaining insight into how deep convolutional neural network models perform image classification and how to explain their outputs have been a concern to computer vision researchers and decision makers. These deep models are often referred to as black box due to low comprehension of their internal workings. As an effort to developing explainable deep learning models, several methods have been proposed such as finding gradients of class output with respect to input image (sensitivity maps), class activation map (CAM), and Gradient based Class Activation Maps (Grad-CAM). These methods under perform…
Image representations, from SIFT and bag of visual words to Convolutional Neural Networks (CNNs) are a crucial component of almost all computer vision systems. However, our understanding of them remains limited. In this paper we study several landmark representations, both shallow and deep, by a number of complementary visualization techniques. These visualizations are based on the concept of "natural pre-image", namely a natural-looking image whose representation has some notable property. We study in particular three such visualizations: inversion, in which the aim is to reconstruct an image…
We demonstrate a recognition and feature visualization method that uses a deep convolutional neural network for Raman spectrum analysis. The visualization is achieved by calculating important regions in the spectra from weights in pooling and fully-connected layers. The method is first examined for simple Lorentzian spectra, then applied to the spectra of pharmaceutical compounds and numerically mixed amino acids. We investigate the effects of the size and number of convolution filters on the extracted regions for Raman-peak signals using the Lorentzian spectra. It is confirmed that the Raman …
This document will review the most prominent proposals using multilayer convolutional architectures. Importantly, the various components of a typical convolutional network will be discussed through a review of different approaches that base their design decisions on biological findings and/or sound theoretical bases. In addition, the different attempts at understanding ConvNets via visualizations and empirical studies will be reviewed. The ultimate goal is to shed light on the role of each layer of processing involved in a ConvNet architecture, distill what we currently understand about ConvNe…
Understanding the internal process of ConvNets is commonly done using visualization techniques. However, these techniques do not usually provide a tool for estimating the stability of a ConvNet against noise. In this paper, we show how to analyze a ConvNet in the frequency domain using a 4-dimensional visualization technique. Using the frequency domain analysis, we show the reason that a ConvNet might be sensitive to a very low magnitude additive noise. Our experiments on a few ConvNets trained on different datasets revealed that convolution kernels of a trained ConvNet usually pass most of th…
The School of Computer Science, Tel Aviv University（特拉维夫大学计算机科学学院）
Neural network visualization techniques mark image locations by their relevancy to the network's classification. Existing methods are effective in highlighting the regions that affect the resulting classification the most. However, as we show, these methods are limited in their ability to identify the support for alternative classifications, an effect we name {\em the saliency bias} hypothesis. In this work, we integrate two lines of research: gradient-based methods and attribution-based methods, and develop an algorithm that provides per-class explainability. The algorithm back-projects the p…
Indian Institute of Science（印度科学学院）；Indian Institute of Technology Bombay（印度理工学院孟买分校）
In this paper, we propose a data-free method of extracting Impressions of each class from the classifier's memory. The Deep Learning regime empowers classifiers to extract distinct patterns (or features) of a given class from training data, which is the basis on which they generalize to unseen data. Before deploying these models on critical applications, it is advantageous to visualize the features considered to be essential for classification. Existing visualization methods develop high confidence images consisting of both background and foreground features. This makes it hard to judge what t…
Despite the effectiveness of Convolutional Neural Networks (CNNs) for image classification, our understanding of the relationship between shape of convolution kernels and learned representations is limited. In this work, we explore and employ the relationship between shape of kernels which define Receptive Fields (RFs) in CNNs for learning of feature representations and image classification. For this purpose, we first propose a feature visualization method for visualization of pixel-wise classification score maps of learned features. Motivated by our experimental results, and observations repo…
We present Convolutional Mean (CM) - a simple and fast convolutional neural network for illuminant estimation. Our proposed method only requires a small neural network model (1.1K parameters) and a 48 x 32 thumbnail input image. Our unoptimized Python implementation takes 1 ms/image, which is arguably 3-3750x faster than the current leading solutions with similar accuracy. Using two public datasets, we show that our proposed light-weight method offers accuracy comparable to the current leading methods' (which consist of thousands/millions of parameters) across several measures.
A standard deep convolutional neural network paired with a suitable loss function learns compact local image descriptors that perform comparably to state-of-the art approaches.
Charité – Universitätsmedizin Berlin（柏林夏里特医学院）；Freie Universität Berlin（柏林自由大学）；Humboldt-Universität zu Berlin（柏林洪堡大学）；Berlin Institute of Health（柏林健康研究所）；Bernstein Center for Computational Neuroscience（伯恩斯坦计算神经科学中心）；Berlin Center for Advanced Neuroimaging（柏林高级神经影像中心）；Technical University Berlin（柏林工业大学）
Visualizing and interpreting convolutional neural networks (CNNs) is an important task to increase trust in automatic medical decision making systems. In this study, we train a 3D CNN to detect Alzheimer's disease based on structural MRI scans of the brain. Then, we apply four different gradient-based and occlusion-based visualization methods that explain the network's classification decisions by highlighting relevant areas in the input image. We compare the methods qualitatively and quantitatively. We find that all four methods focus on brain regions known to be involved in Alzheimer's diseas…
Radboud University Medical Center（拉德堡德大学医学中心）；Computational Pathology Group（计算病理学小组）
To train deep convolutional neural networks, the input data and the intermediate activations need to be kept in memory to calculate the gradient descent step. Given the limited memory available in the current generation accelerator cards, this limits the maximum dimensions of the input data. We demonstrate a method to train convolutional neural networks holding only parts of the image in memory while giving equivalent results. We quantitatively compare this new way of training convolutional neural networks with conventional training. In addition, as a proof of concept, we train a convolutional…
Georgia Tech（佐治亚理工学院）；Oregon State University（俄勒冈州立大学）
Deep learning's great success motivates many practitioners and students to learn about this exciting technology. However, it is often challenging for beginners to take their first step due to the complexity of understanding and applying deep learning. We present CNN Explainer, an interactive visualization tool designed for non-experts to learn and examine convolutional neural networks (CNNs), a foundational deep learning model architecture. Our tool addresses key challenges that novices face while learning about CNNs, which we identify from interviews with instructors and a survey with past st…
Trained on the works of an artist under study and visually comparable works of other artists, convolutional neural networks can identify forgeries and provide attributions. They can also assign classification probabilities within a painting, revealing mixed authorship and identifying regions painted by different hands.
Institution of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Convolutional kernels are basic and vital components of deep Convolutional Neural Networks (CNN). In this paper, we equip convolutional kernels with shape attributes to generate the deep Irregular Convolutional Neural Networks (ICNN). Compared to traditional CNN applying regular convolutional kernels like ${3\times3}$, our approach trains irregular kernel shapes to better fit the geometric variations of input features. In other words, shapes are learnable parameters in addition to weights. The kernel shapes and weights are learned simultaneously during end-to-end training with the standard bac…
Politecnico di Milano（米兰理工大学）；University of Montreal（蒙特利尔大学）
In this paper, we propose a deep neural network architecture for object recognition based on recurrent neural networks. The proposed network, called ReNet, replaces the ubiquitous convolution+pooling layer of the deep convolutional neural network with four recurrent neural networks that sweep horizontally and vertically in both directions across the image. We evaluate the proposed ReNet on three widely-used benchmark datasets; MNIST, CIFAR-10 and SVHN. The result suggests that ReNet is a viable alternative to the deep convolutional neural network, and that further investigation is needed.
Centre for Integrative Neuroscience（综合神经科学中心）；Institute for Theoretical Physics（理论物理研究所）；Bernstein Center for Computational Neuroscience（伯恩斯坦计算神经科学中心）；University of Tübingen（图宾根大学）
Visualizing features in deep neural networks (DNNs) can help understanding their computations. Many previous studies aimed to visualize the selectivity of individual units by finding meaningful images that maximize their activation. However, comparably little attention has been paid to visualizing to what image transformations units in DNNs are invariant. Here we propose a method to discover invariances in the responses of hidden layer units of deep neural networks. Our approach is based on simultaneously searching for a batch of images that strongly activate a unit while at the same time bein…
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.
This article presents the design, experiments and results of our solution submitted to the 2018 ISIC challenge: Skin Lesion Analysis Towards Melanoma Detection. We design a pipeline using state-of-the-art Convolutional Neural Network (CNN) models for a Lesion Boundary Segmentation task and a Lesion Diagnosis task.
We propose a visualization technique that utilizes neural network embeddings and a generative network to reconstruct original data. This method allows for independent manipulation of individual image embeddings through its non-parametric structure, providing more flexibility than traditional autoencoder approaches. We have evaluated the effectiveness of this technique in data visualization and compared it to t-SNE and VAE methods. Furthermore, we have demonstrated the scalability of our method through visualizations on the ImageNet dataset. Our technique has potential applications in human-in-…
In this project we work on creating a model to classify images for the Pascal VOC Challenge 2012. We use convolutional neural networks trained on a single GPU instance provided by Amazon via their cloud service Amazon Web Services (AWS) to classify images in the Pascal VOC 2012 data set. We train multiple convolutional neural network models and finally settle on the best model which produced a validation accuracy of 85.6% and a testing accuracy of 85.24%.
We have implemented a convolutional neural network designed for processing sparse three-dimensional input data. The world we live in is three dimensional so there are a large number of potential applications including 3D object recognition and analysis of space-time objects. In the quest for efficiency, we experiment with CNNs on the 2D triangular-lattice and 3D tetrahedral-lattice.
Taras Shevchenko National University of Kyiv（基辅塔拉斯·舍甫琴科国立大学）
At this work we introduce horizontally symmetric convolutional kernels for CNNs which make the network output invariant to horizontal flips of the image. We also study other types of symmetric kernels which lead to vertical flip invariance, and approximate rotational invariance. We show that usage of such kernels acts as regularizer, and improves generalization of the convolutional neural networks at the cost of more complicated training process.
Large Convolutional Network models have recently demonstrated impressive classification performance on the ImageNet benchmark. However there is no clear understanding of why they perform so well, or how they might be improved. In this paper we address both issues. We introduce a novel visualization technique that gives insight into the function of intermediate feature layers and the operation of the classifier. We also perform an ablation study to discover the performance contribution from different model layers. This enables us to find model architectures that outperform Krizhevsky \etal on t…
Activation functions play a vital role in the training of Convolutional Neural Networks. For this reason, to develop efficient and performing functions is a crucial problem in the deep learning community. Key to these approaches is to permit a reliable parameter learning, avoiding vanishing gradient problems. The goal of this work is to propose an ensemble of Convolutional Neural Networks trained using several different activation functions. Moreover, a novel activation function is here proposed for the first time. Our aim is to improve the performance of Convolutional Neural Networks in small…
One of the methods used in image recognition is the Deep Convolutional Neural Network (DCNN). DCNN is a model in which the expressive power of features is greatly improved by deepening the hidden layer of CNN. The architecture of CNNs is determined based on a model of the visual cortex of mammals. There is a model called Residual Network (ResNet) that has a skip connection. ResNet is an advanced model in terms of the learning method, but it has not been interpreted from a biological viewpoint. In this research, we investigate the receptive fields of a ResNet on the classification task in Image…
Fundação Oswaldo Cruz, Instituto Gonçalo Moniz（奥斯瓦尔多·克鲁兹基金会，贡萨洛·莫尼兹研究所）；Universidade Federal de Estadual de Feira de Santana（费拉迪圣安娜州立联邦大学）
This letter presente a comment on the paper Prediction of Kidney Function from Biopsy Images using Convolutional Neural Networks by Ledbetter et al. (2017)
In this technical report, we investigate extending convolutional neural networks to the setting where functions are not sampled in a grid pattern. We show that by treating the samples as the average of a function within a cell, we can find a natural equivalent of most layers used in CNN. We also present an algorithm for running inference for these models exactly using standard convex geometry algorithms.
Quantitative analysis of brain MRI at the age of 6 months is difficult because of the limited contrast between white matter and gray matter. In this study, we use a dilated triplanar convolutional neural network in combination with a non-dilated 3D convolutional neural network for the segmentation of white matter, gray matter and cerebrospinal fluid in infant brain MR images, as provided by the MICCAI grand challenge on 6-month infant brain MRI segmentation.
Rice University（莱斯大学）；Baylor College of Medicine（贝勒医学院）
Backpropagation-based visualizations have been proposed to interpret convolutional neural networks (CNNs), however a theory is missing to justify their behaviors: Guided backpropagation (GBP) and deconvolutional network (DeconvNet) generate more human-interpretable but less class-sensitive visualizations than saliency map. Motivated by this, we develop a theoretical explanation revealing that GBP and DeconvNet are essentially doing (partial) image recovery which is unrelated to the network decisions. Specifically, our analysis shows that the backward ReLU introduced by GBP and DeconvNet, and t…
Microsoft Research（微软研究院）；University of California, Los Angeles（加州大学洛杉矶分校）
The convolutional neural networks (CNNs) have proven to be a powerful tool for discriminative learning. Recently researchers have also started to show interest in the generative aspects of CNNs in order to gain a deeper understanding of what they have learned and how to further improve them. This paper investigates generative modeling of CNNs. The main contributions include: (1) We construct a generative model for the CNN in the form of exponential tilting of a reference distribution. (2) We propose a generative gradient for pre-training CNNs by a non-parametric importance sampling scheme, whi…
The success of deep neural networks is mostly due their ability to learn meaningful features from the data. Features learned in the hidden layers of deep neural networks trained in computer vision tasks have been shown to be similar to mid-level vision features. We leverage this fact in this work and propose the visualization regularizer for image tasks. The proposed regularization technique enforces smoothness of the features learned by hidden nodes and turns out to be a special case of Tikhonov regularization. We achieve higher classification accuracy as compared to existing regularizers suc…
The internal states of most deep neural networks are difficult to interpret, which makes diagnosis and debugging during training challenging. Activation maximization methods are widely used, but lead to multiple optima and are hard to interpret (appear noise-like) for complex neurons. Image-based methods use maximally-activating image regions which are easier to interpret, but do not provide pixel-level insight into why the neuron responds to them. In this work we introduce an MCMC method: Langevin Dynamics Activation Maximization (LDAM), which is designed for diagnostic visualization. LDAM pr…
University of Wyoming（怀俄明大学）；Cornell University（康奈尔大学）
We can better understand deep neural networks by identifying which features each of their neurons have learned to detect. To do so, researchers have created Deep Visualization techniques including activation maximization, which synthetically generates inputs (e.g. images) that maximally activate each neuron. A limitation of current techniques is that they assume each neuron detects only one type of feature, but we know that neurons can be multifaceted, in that they fire in response to many different types of features: for example, a grocery store class neuron must activate either for rows of p…
Picasso is a free open-source (Eclipse Public License) web application written in Python for rendering standard visualizations useful for analyzing convolutional neural networks. Picasso ships with occlusion maps and saliency maps, two visualizations which help reveal issues that evaluation metrics like loss and accuracy might hide: for example, learning a proxy classification task. Picasso works with the Tensorflow deep learning framework, and Keras (when the model can be loaded into the Tensorflow backend). Picasso can be used with minimal configuration by deep learning researchers and engin…
In recent years convolutional neural networks (CNN) have shown striking progress in various tasks. However, despite the high performance, the training and prediction process remains to be a black box, leaving it a mystery to extract what neurons learn in CNN. In this paper, we address the problem of interpreting a CNN from the aspects of the input image's focus and preference, and the neurons' domination, activation and contribution to a concrete final prediction. Specifically, we use two techniques - visualization and clustering - to tackle the problems above. Visualization means the method o…
We present a framework to systematically analyze convolutional neural networks (CNNs) used in classification of cars in autonomous vehicles. Our analysis procedure comprises an image generator that produces synthetic pictures by sampling in a lower dimension image modification subspace and a suite of visualization tools. The image generator produces images which can be used to test the CNN and hence expose its vulnerabilities. The presented framework can be used to extract insights of the CNN classifier, compare across classification models, or generate training and validation datasets.
German Center for Neurodegenerative Diseases (DZNE)（德国神经退行性疾病中心）；University of Rostock（罗斯托克大学）；Charité – Universitätsmedizin Berlin（夏里特医学院）；University Hospital Bonn（波恩大学医院）；Ludwig Maximilian University（慕尼黑大学）；Rostock University Medical Center（罗斯托克大学医学中心）；Georg-August-University（哥廷根大学）；Otto-von-Guericke University（奥托·冯·古里克大学）；Bernstein Center for Computational Neuroscience（伯恩斯坦计算神经科学中心）；Hertie Institute for Clinical Brain Research（赫蒂临床脑研究所）；University of Tuebingen（图宾根大学）；University of Cologne（科隆大学）；Darmstadt University of Technology（达姆施塔特工业大学）；Imperial College London（伦敦帝国理工学院）；Technical University Munich（慕尼黑工业大学）；University Medical Center Goettingen（哥廷根大学医学中心）；Leibniz Institute for Neurobiology（莱布尼茨神经生物学研究所）；University of Toronto（多伦多大学）；University of Aveiro（阿威罗大学）
Background: Although convolutional neural networks (CNN) achieve high diagnostic accuracy for detecting Alzheimer's disease (AD) dementia based on magnetic resonance imaging (MRI) scans, they are not yet applied in clinical routine. One important reason for this is a lack of model comprehensibility. Recently developed visualization methods for deriving CNN relevance maps may help to fill this gap. We investigated whether models with higher accuracy also rely more on discriminative brain regions predefined by prior knowledge. Methods: We trained a CNN for the detection of AD in N=663 T1-weighte…
