The encoding of local features is an essential part for writer identification and writer retrieval. While CNN activations have already been used as local features in related works, the encoding of these features has attracted little attention so far. In this work, we compare the established VLAD encoding with triangulation embedding. We further investigate generalized max pooling as an alternative to sum pooling and the impact of decorrelation and Exemplar SVMs. With these techniques, we set new standards on two publicly available datasets (ICDAR13, KHATT).
Shenzhen Institutes of Advanced Technology, CAS（中国科学院深圳先进技术研究院）；University of Chinese Academy of Sciences（中国科学院大学）；The Chinese University of Hong Kong（香港中文大学）
Text-independent writer identification is challenging due to the huge variation of written contents and the ambiguous written styles of different writers. This paper proposes DeepWriter, a deep multi-stream CNN to learn deep powerful representation for recognizing writers. DeepWriter takes local handwritten patches as input and is trained with softmax classification loss. The main contributions are: 1) we design and optimize multi-stream structure for writer identification task; 2) we introduce data augmentation learning to enhance the performance of DeepWriter; 3) we introduce a patch scannin…
National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China（中国科学技术大学语音及语言信息处理国家工程实验室）
Recently, the hybrid convolutional neural network hidden Markov model (CNN-HMM) has been introduced for offline handwritten Chinese text recognition (HCTR) and has achieved state-of-the-art performance. However, modeling each of the large vocabulary of Chinese characters with a uniform and fixed number of hidden states requires high memory and computational costs and makes the tens of thousands of HMM state classes confusing. Another key issue of CNN-HMM for HCTR is the diversified writing style, which leads to model strain and a significant performance decline for specific writers. To address…
Most existing online writer-identification systems require that the text content is supplied in advance and rely on separately designed features and classifiers. The identifications are based on lines of text, entire paragraphs, or entire documents; however, these materials are not always available. In this paper, we introduce a path-signature feature to an end-to-end text-independent writer-identification system with a deep convolutional neural network (DCNN). Because deep models require a considerable amount of data to achieve good performance, we propose a data-augmentation method named Dro…
The use of features extracted using a deep convolutional neural network (CNN) combined with a writer-dependent (WD) SVM classifier resulted in significant improvement in performance of handwritten signature verification (HSV) when compared to the previous state-of-the-art methods. In this work it is investigated whether the use of these CNN features provide good results in a writer-independent (WI) HSV context, based on the dichotomy transformation combined with the use of an SVM writer-independent classifier. The experiments performed in the Brazilian and GPDS datasets show that (i) the propo…
Indian Statistical Institute（印度统计研究所）；Østfold University College（东福尔德大学学院）
Text independent writer identification is a challenging problem that differentiates between different handwriting styles to decide the author of the handwritten text. Earlier writer identification relied on handcrafted features to reveal pieces of differences between writers. Recent work with the advent of convolutional neural network, deep learning-based methods have evolved. In this paper, three different deep learning techniques - spatial attention mechanism, multi-scale feature fusion and patch-based CNN were proposed to effectively capture the difference between each writer's handwriting.…
Tokyo University of Agriculture and Technology (TUAT)（东京农工大学）；Jagiellonian University（雅盖隆大学）；Institute of Philosophy（哲学研究所）
The text-independent approach to writer identification does not require the writer to write some predetermined text. Previous research on text-independent writer identification has been based on identifying writer-specific features designed by experts. However, in the last decade, deep learning methods have been successfully applied to learn features from data automatically. We propose here an end-to-end deep-learning method for text-independent writer identification that does not require prior identification of features. A Convolutional Neural Network (CNN) is trained initially to extract loc…
Owing to the rapid growth of touchscreen mobile terminals and pen-based interfaces, handwriting-based writer identification systems are attracting increasing attention for personal authentication, digital forensics, and other applications. However, most studies on writer identification have not been satisfying because of the insufficiency of data and difficulty of designing good features under various conditions of handwritings. Hence, we introduce an end-to-end system, namely DeepWriterID, employed a deep convolutional neural network (CNN) to address these problems. A key feature of DeepWrite…
University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Deep convolutional neural networks (CNN) have shown their promise as a universal representation for recognition. However, global CNN activations lack geometric invariance, which limits their robustness for classification and matching of highly variable scenes. To improve the invariance of CNN activations without degrading their discriminative power, this paper presents a simple but effective scheme called multi-scale orderless pooling (MOP-CNN). This scheme extracts CNN activations for local patches at multiple scale levels, performs orderless VLAD pooling of these activations at each level se…
Indian Institute of Technology Guwahati（印度理工学院古瓦哈提分校）
Handwriting recognition is one of the desirable attributes of document comprehension and analysis. It is concerned with the documents writing style and characteristics that distinguish the authors. The diversity of text images, notably in images with varying handwriting, makes the process of learning good features difficult in cases where little data is available. In this paper, we propose a novel scheme to identify the author of a document based on the input word image. Our method is text independent and does not impose any constraint on the size of the input image under examination. To begin…
Deep learning models have shown their superior performance in various vision tasks. However, the lack of precisely interpreting kernels in convolutional neural networks (CNNs) is becoming one main obstacle to wide applications of deep learning models in real scenarios. Although existing interpretation methods may find certain visual patterns which are associated with the activation of a specific kernel, those visual patterns may not be specific or comprehensive enough for interpretation of a specific activation of kernel of interest. In this paper, a simple yet effective optimization method is…
Center for Machine Perception（机器感知中心）；FEE CTU Prague（捷克布拉格技术大学电子工程学院）；Irisa Rennes（雷恩信息与随机系统研究所）；Facebook AI Research（脸书人工智能研究院）；Inria（法国国家信息与自动化研究所）
Recently, image representation built upon Convolutional Neural Network (CNN) has been shown to provide effective descriptors for image search, outperforming pre-CNN features as short-vector representations. Yet such models are not compatible with geometry-aware re-ranking methods and still outperformed, on some particular object retrieval benchmarks, by traditional image search systems relying on precise descriptor matching, geometric re-ranking, or query expansion. This work revisits both retrieval stages, namely initial search and re-ranking, by employing the same primitive information deriv…
The purpose of mid-level visual element discovery is to find clusters of image patches that are both representative and discriminative. Here we study this problem from the prospective of pattern mining while relying on the recently popularized Convolutional Neural Networks (CNNs). We observe that a fully-connected CNN activation extracted from an image patch typically possesses two appealing properties that enable its seamless integration with pattern mining techniques. The marriage between CNN activations and association rule mining, a well-known pattern mining technique in the literature, le…
Neural networks have shown to be a practical way of building a very complex mapping between a pre-specified input space and output space. For example, a convolutional neural network (CNN) mapping an image into one of a thousand object labels is approaching human performance in this particular task. However the mapping (neural network) does not automatically lend itself to other forms of queries, for example, to detect/reconstruct object instances, to enforce top-down signal on ambiguous inputs, or to recover object instances from occlusion. One way to address these queries is a backward pass t…
Technion（以色列理工学院）；Habana Labs — An Intel Company（Habana Labs — 英特尔公司）
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…
The area of Handwritten Signature Verification has been broadly researched in the last decades, but remains an open research problem. In offline (static) signature verification, the dynamic information of the signature writing process is lost, and it is difficult to design good feature extractors that can distinguish genuine signatures and skilled forgeries. This verification task is even harder in writer independent scenarios which is undeniably fiscal for realistic cases. In this paper, we have proposed an Ensemble model for offline writer, independent signature verification task with Deep l…
The reason behind CNNs capability to learn high-dimensional complex features from the images is the non-linearity introduced by the activation function. Several advanced activation functions have been discovered to improve the training process of neural networks, as choosing an activation function is a crucial step in the modeling. Recent research has proposed using an oscillating activation function to solve classification problems inspired by the human brain cortex. This paper explores the performance of one of the CNN architecture ALexNet on MNIST and CIFAR10 datasets using oscillatory acti…
We propose a novel CNN architecture called ACTNET for robust instance image retrieval from large-scale datasets. Our key innovation is a learnable activation layer designed to improve the signal-to-noise ratio (SNR) of deep convolutional feature maps. Further, we introduce a controlled multi-stream aggregation, where complementary deep features from different convolutional layers are optimally transformed and balanced using our novel activation layers, before aggregation into a global descriptor. Importantly, the learnable parameters of our activation blocks are explicitly trained, together wi…
A main issue preventing the use of Convolutional Neural Networks (CNN) in end user applications is the low level of transparency in the decision process. Previous work on CNN interpretability has mostly focused either on localizing the regions of the image that contribute to the result or on building an external model that generates plausible explanations. However, the former does not provide any semantic information and the latter does not guarantee the faithfulness of the explanation. We propose an intermediate representation composed of multiple Semantically Interpretable Activation Maps (S…
In the current research of neural networks, the activation function is manually specified by human and not able to change themselves during training. This paper focus on how to make the activation function trainable for deep neural networks. We use series and linear combination of different activation functions make activation functions continuously variable. Also, we test the performance of CNNs with Fourier series simulated activation(Fourier-CNN) and CNNs with linear combined activation function (LC-CNN) on Cifar-10 dataset. The result shows our trainable activation function reveals better …
Hong Kong University of Science and Technology（香港科技大学）；Tencent AI lab（腾讯人工智能实验室）；Huazhong University of Science and Technology（华中科技大学）
In this work, we study the 1-bit convolutional neural networks (CNNs), of which both the weights and activations are binary. While being efficient, the classification accuracy of the current 1-bit CNNs is much worse compared to their counterpart real-valued CNN models on the large-scale dataset, like ImageNet. To minimize the performance gap between the 1-bit and real-valued CNN models, we propose a novel model, dubbed Bi-Real net, which connects the real activations (after the 1-bit convolution and/or BatchNorm layer, before the sign function) to activations of the consecutive block, through …
University of Padua（帕多瓦大学）；Missouri State University（密苏里州立大学）；Tampere University（坦佩雷大学）
Recently, much attention has been devoted to finding highly efficient and powerful activation functions for CNN layers. Because activation functions inject different nonlinearities between layers that affect performance, varying them is one method for building robust ensembles of CNNs. The objective of this study is to examine the performance of CNN ensembles made with different activation functions, including six new ones presented here: 2D Mexican ReLU, TanELU, MeLU+GaLU, Symmetric MeLU, Symmetric GaLU, and Flexible MeLU. The highest performing ensemble was built with CNNs having different a…
Utrecht University（乌得勒支大学）；University of Warwick（华威大学）
Convolutional Neural Networks (CNNs) use pooling to decrease the size of activation maps. This process is crucial to increase the receptive fields and to reduce computational requirements of subsequent convolutions. An important feature of the pooling operation is the minimization of information loss, with respect to the initial activation maps, without a significant impact on the computation and memory overhead. To meet these requirements, we propose SoftPool: a fast and efficient method for exponentially weighted activation downsampling. Through experiments across a range of architectures an…
The large amount of memory bandwidth between local buffer and external DRAM has become the speedup bottleneck of CNN hardware accelerators, especially for activation maps. To reduce memory bandwidth, we propose to learn pruning unimportant blocks dynamically with zero block regularization of activation maps (Zebra). This strategy has low computational overhead and could easily integrate with other pruning methods for better performance. The experimental results show that the proposed method can reduce 70\% of memory bandwidth for Resnet-18 on Tiny-Imagenet within 1\% accuracy drops and 2\% acc…
Training Convolutional Neural Networks (CNN) is a resource intensive task that requires specialized hardware for efficient computation. One of the most limiting bottleneck of CNN training is the memory cost associated with storing the activation values of hidden layers needed for the computation of the weights gradient during the backward pass of the backpropagation algorithm. Recently, reversible architectures have been proposed to reduce the memory cost of training large CNN by reconstructing the input activation values of hidden layers from their output during the backward pass, circumventi…
Sparsification is an efficient approach to accelerate CNN inference, but it is challenging to take advantage of sparsity in training procedure because the involved gradients are dynamically changed. Actually, an important observation shows that most of the activation gradients in back-propagation are very close to zero and only have a tiny impact on weight-updating. Hence, we consider pruning these very small gradients randomly to accelerate CNN training according to the statistical distribution of activation gradients. Meanwhile, we theoretically analyze the impact of pruning algorithm on the…
Technische Hochschule Ingolstadt（英戈尔施塔特应用技术大学）；Royal Melbourne Institute of Technology（皇家墨尔本理工大学）
Traffic scenario categorisation is an essential component of automated driving, for e.\,g., in motion planning algorithms and their validation. Finding new relevant scenarios without handcrafted steps reduce the required resources for the development of autonomous driving dramatically. In this work, a method is proposed to address this challenge by introducing a clustering technique based on a novel data-adaptive similarity measure, called Random Forest Activation Pattern (RFAP) similarity. The RFAP similarity is generated using a tree encoding scheme in a Random Forest algorithm. The clusteri…
For many biological image segmentation tasks, including topological knowledge, such as the nesting of classes, can greatly improve results. However, most `out-of-the-box' CNN models are still blind to such prior information. In this paper, we propose a novel approach to encode this information, through a multi-level activation layer and three compatible losses. We benchmark all of them on nuclei segmentation in bright-field microscopy cell images from the 2018 Data Science Bowl challenge, offering an exemplary segmentation task with cells and nested subcellular structures. Our scheme greatly s…
Fudan University（复旦大学）；Rensselaer Polytechnic Institute（伦斯勒理工学院）；Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）
A number of studies on lung nodule classification lack clinical/biological interpretations of the features extracted by convolutional neural network (CNN). The methods like class activation mapping (CAM) and gradient-based CAM (Grad-CAM) are tailored for interpreting localization and classification tasks while they ignored fine-grained features. Therefore, CAM and Grad-CAM cannot provide optimal interpretation for lung nodule categorization task in low-dose CT images, in that fine-grained pathological clues like discrete and irregular shape and margins of nodules are capable of enhancing sensi…
Convolutional neural network (CNN) models for computer vision are powerful but lack explainability in their most basic form. This deficiency remains a key challenge when applying CNNs in important domains. Recent work on explanations through feature importance of approximate linear models has moved from input-level features (pixels or segments) to features from mid-layer feature maps in the form of concept activation vectors (CAVs). CAVs contain concept-level information and could be learned via clustering. In this work, we rethink the ACE algorithm of Ghorbani et~al., proposing an alternative…
Idiap Research Institute（伊迪亚普研究所）；École Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院）；University of Rome La Sapienza（罗马第一大学）
Since Convolutional Neural Networks (CNNs) have become the leading learning paradigm in visual recognition, Naive Bayes Nearest Neighbour (NBNN)-based classifiers have lost momentum in the community. This is because (1) such algorithms cannot use CNN activations as input features; (2) they cannot be used as final layer of CNN architectures for end-to-end training , and (3) they are generally not scalable and hence cannot handle big data. This paper proposes a framework that addresses all these issues, thus bringing back NBNNs on the map. We solve the first by extracting CNN activations from lo…
National Laboratory of Pattern Recognition, CASIA（中国科学院自动化研究所模式识别国家重点实验室）；Center for Research on Intelligent Perception and Computing, CASIA（中国科学院自动化研究所智能感知与计算研究中心）；Center for Excellence in Brain Science and Intelligence Technology, CAS（中国科学院脑科学与智能技术卓越创新中心）；University of Chinese Academy of Sciences（中国科学院大学）
The volume of convolutional neural network (CNN) models proposed for face recognition has been continuously growing larger to better fit large amount of training data. When training data are obtained from internet, the labels are likely to be ambiguous and inaccurate. This paper presents a Light CNN framework to learn a compact embedding on the large-scale face data with massive noisy labels. First, we introduce a variation of maxout activation, called Max-Feature-Map (MFM), into each convolutional layer of CNN. Different from maxout activation that uses many feature maps to linearly approxima…
Privacy-Preserving Machine Learning algorithms must balance classification accuracy with data privacy. This can be done using a combination of cryptographic and machine learning tools such as Convolutional Neural Networks (CNN). CNNs typically consist of two types of operations: a convolutional or linear layer, followed by a non-linear function such as ReLU. Each of these types can be implemented efficiently using a different cryptographic tool. But these tools require different representations and switching between them is time-consuming and expensive. Recent research suggests that ReLU is re…
Compared to image representation based on low-level local descriptors, deep neural activations of Convolutional Neural Networks (CNNs) are richer in mid-level representation, but poorer in geometric invariance properties. In this paper, we present a straightforward framework for better image representation by combining the two approaches. To take advantages of both representations, we propose an efficient method to extract a fair amount of multi-scale dense local activations from a pre-trained CNN. We then aggregate the activations by Fisher kernel framework, which has been modified with a sim…
Along with data on the web increasing dramatically, hashing is becoming more and more popular as a method of approximate nearest neighbor search. Previous supervised hashing methods utilized similarity/dissimilarity matrix to get semantic information. But the matrix is not easy to construct for a new dataset. Rather than to reconstruct the matrix, we proposed a straightforward CNN-based hashing method, i.e. binarilizing the activations of a fully connected layer with threshold 0 and taking the binary result as hash codes. This method achieved the best performance on CIFAR-10 and was comparable…
This paper evaluates whether training a decision tree based on concepts extracted from a concept-based explainer can increase interpretability for Convolutional Neural Networks (CNNs) models and boost the fidelity and performance of the used explainer. CNNs for computer vision have shown exceptional performance in critical industries. However, it is a significant barrier when deploying CNNs due to their complexity and lack of interpretability. Recent studies to explain computer vision models have shifted from extracting low-level features (pixel-based explanations) to mid-or high-level feature…
Deep convolutional neural network (CNN) inference requires significant amount of memory and computation, which limits its deployment on embedded devices. To alleviate these problems to some extent, prior research utilize low precision fixed-point numbers to represent the CNN weights and activations. However, the minimum required data precision of fixed-point weights varies across different networks and also across different layers of the same network. In this work, we propose using floating-point numbers for representing the weights and fixed-point numbers for representing the activations. We …
In this paper, we address the problem of image retrieval by learning images representation based on the activations of a Convolutional Neural Network. We present an end-to-end trainable network architecture that exploits a novel multi-scale local pooling based on NetVLAD and a triplet mining procedure based on samples difficulty to obtain an effective image representation. Extensive experiments show that our approach is able to reach state-of-the-art results on three standard datasets.
Convolutional Neural Network's (CNN's) performance disparity on clean and corrupted datasets has recently come under scrutiny. In this work, we analyse common corruptions in the frequency domain, i.e., High Frequency corruptions (HFc, e.g., noise) and Low Frequency corruptions (LFc, e.g., blur). Although a simple solution to HFc is low-pass filtering, ReLU -- a widely used Activation Function (AF), does not have any filtering mechanism. In this work, we instill low-pass filtering into the AF (LP-ReLU) to improve robustness against HFc. To deal with LFc, we complement LP-ReLU with Discrete Cosi…
Technische Universität Darmstadt（达姆施塔特工业大学）；University of Tübingen（图宾根大学）
Feature visualizations such as synthetic maximally activating images are a widely used explanation method to better understand the information processing of convolutional neural networks (CNNs). At the same time, there are concerns that these visualizations might not accurately represent CNNs' inner workings. Here, we measure how much extremely activating images help humans to predict CNN activations. Using a well-controlled psychophysical paradigm, we compare the informativeness of synthetic images by Olah et al. (2017) with a simple baseline visualization, namely exemplary natural images tha…
Convolutional Neural Networks (CNNs) are powerful models that achieve impressive results for image classification. In addition, pre-trained CNNs are also useful for other computer vision tasks as generic feature extractors. This paper aims to gain insight into the feature aspect of CNN and demonstrate other uses of CNN features. Our results show that CNN feature maps can be used with Random Forests and SVM to yield classification results that outperforms the original CNN. A CNN that is less than optimal (e.g. not fully trained or overfitting) can also extract features for Random Forest/SVM tha…
University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；University of Kansas Medical Center（堪萨斯大学医学中心）；UCLA David Geffen School of Medicine（加州大学洛杉矶分校大卫·格芬医学院）；Baylor College of Medicine（贝勒医学院）
This work presents a mitosis detection method with only one vanilla Convolutional Neural Network (CNN). Our method consists of two steps: given an image, we first apply a CNN using a sliding window technique to extract patches that have mitoses; we then calculate each extracted patch's class activation map to obtain the mitosis's precise location. To increase the model performance on high-domain-variance pathology images, we train the CNN with a data augmentation pipeline, a noise-tolerant loss that copes with unlabeled images, and a multi-rounded active learning strategy. In the MIDOG 2022 ch…
Deep learning models suffer from opaqueness. For Convolutional Neural Networks (CNNs), current research strategies for explaining models focus on the target classes within the associated training dataset. As a result, the understanding of hidden feature map activations is limited by the discriminative knowledge gleaned during training. The aim of our work is to explain and expand CNNs models via the mirroring or alignment of CNN to an external knowledge base. This will allow us to give a semantic context or label for each visual feature. We can match CNN feature activations to nodes in our ext…
Recognizing objects and scenes are two challenging but essential tasks in image understanding. In particular, the use of RGB-D sensors in handling these tasks has emerged as an important area of focus for better visual understanding. Meanwhile, deep neural networks, specifically convolutional neural networks (CNNs), have become widespread and have been applied to many visual tasks by replacing hand-crafted features with effective deep features. However, it is an open problem how to exploit deep features from a multi-layer CNN model effectively. In this paper, we propose a novel two-stage frame…
Hanbat National University（韩bat国立大学）；Lunit Inc.（Lunit公司）
We propose Sequential Feature Filtering Classifier (FFC), a simple but effective classifier for convolutional neural networks (CNNs). With sequential LayerNorm and ReLU, FFC zeroes out low-activation units and preserves high-activation units. The sequential feature filtering process generates multiple features, which are fed into a shared classifier for multiple outputs. FFC can be applied to any CNNs with a classifier, and significantly improves performances with negligible overhead. We extensively validate the efficacy of FFC on various tasks: ImageNet-1K classification, MS COCO detection, C…
Visual interpretability of Convolutional Neural Networks (CNNs) has gained significant popularity because of the great challenges that CNN complexity imposes to understanding their inner workings. Although many techniques have been proposed to visualize class features of CNNs, most of them do not provide a correspondence between inputs and the extracted features in specific layers. This prevents the discovery of stimuli that each layer responds better to. We propose an approach to visually interpret CNN features given a set of images by creating corresponding images that depict the most inform…
