PyTorchKR Papers

최신 논문

총 12,350편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1904.02454

Active Transfer Learning Network: A Unified Deep Joint Spectral-Spatial Feature Learning Model For Hyperspectral Image Classification

Deep learning has recently attracted significant attention in the field of hyperspectral images (HSIs) classification. However, the construction of an efficient deep neural network (DNN) mostly relies on a large number of labeled samples being available. To address this problem, this paper proposes a unified deep network, combined with active transfer learning that can be well-trained for HSIs classification using only minimally labeled training data. More specifically, deep joint spectral-spatial feature is first extracted through hierarchical stacked sparse autoencoder (SSAE) networks. Active transfer learning is then exploited to transfer the pre-trained SSAE network and the limited training samples from the source domain to the target domain, where the SSAE network is subsequently fine-tuned using the limited labeled samples selected from both source and target domain by corresponding active learning strategies. The advantages of our proposed method are threefold: 1) the network can be effectively trained using only limited labeled samples with the help of novel active learning strategies; 2) the network is flexible and scalable enough to function across various transfer situations, including cross-dataset and intra-image; 3) the learned deep joint spectral-spatial feature representation is more generic and robust than many joint spectral-spatial feature representation. Extensive comparative evaluations demonstrate that our proposed method significantly outperforms many state-of-the-art approaches, including both traditional and deep network-based methods, on three popular datasets.

arXiv:1904.02420

Transfer Learning with Sparse Associative Memories

In this paper, we introduce a novel layer designed to be used as the output of pre-trained neural networks in the context of classification. Based on Associative Memories, this layer can help design Deep Neural Networks which support incremental learning and that can be (partially) trained in real time on embedded devices. Experiments on the ImageNet dataset and other different domain specific datasets show that it is possible to design more flexible and faster-to-train Neural Networks at the cost of a slight decrease in accuracy.

arXiv:1904.02418

Learning to Decipher Hate Symbols

Existing computational models to understand hate speech typically frame the problem as a simple classification task, bypassing the understanding of hate symbols (e.g., 14 words, kigy) and their secret connotations. In this paper, we propose a novel task of deciphering hate symbols. To do this, we leverage the Urban Dictionary and collected a new, symbol-rich Twitter corpus of hate speech. We investigate neural network latent context models for deciphering hate symbols. More specifically, we study Sequence-to-Sequence models and show how they are able to crack the ciphers based on context. Furthermore, we propose a novel Variational Decipher and show how it can generalize better to unseen hate symbols in a more challenging testing setting.

arXiv:1904.02375공식 코드 · Papers with Code

ConvPoint: Continuous Convolutions for Point Cloud Processing

Point clouds are unstructured and unordered data, as opposed to images. Thus, most machine learning approach developed for image cannot be directly transferred to point clouds. In this paper, we propose a generalization of discrete convolutional neural networks (CNNs) in order to deal with point clouds by replacing discrete kernels by continuous ones. This formulation is simple, allows arbitrary point cloud sizes and can easily be used for designing neural networks similarly to 2D CNNs. We present experimental results with various architectures, highlighting the flexibility of the proposed approach. We obtain competitive results compared to the state-of-the-art on shape classification, part segmentation and semantic segmentation for large-scale point clouds.

arXiv:1904.02365공식 코드 · Papers with Code

Template-Based Automatic Search of Compact Semantic Segmentation Architectures

Automatic search of neural architectures for various vision and natural language tasks is becoming a prominent tool as it allows to discover high-performing structures on any dataset of interest. Nevertheless, on more difficult domains, such as dense per-pixel classification, current automatic approaches are limited in their scope - due to their strong reliance on existing image classifiers they tend to search only for a handful of additional layers with discovered architectures still containing a large number of parameters. In contrast, in this work we propose a novel solution able to find light-weight and accurate segmentation architectures starting from only few blocks of a pre-trained classification network. To this end, we progressively build up a methodology that relies on templates of sets of operations, predicts which template and how many times should be applied at each step, while also generating the connectivity structure and downsampling factors. All these decisions are being made by a recurrent neural network that is rewarded based on the score of the emitted architecture on the holdout set and trained using reinforcement learning. One discovered architecture achieves 63.2% mean IoU on CamVid and 67.8% on CityScapes having only 270K parameters. Pre-trained models and the search code are available at https://github.com/DrSleep/nas-segm-pytorch.

arXiv:1904.02322공식 코드 · Papers with Code

Modified Distribution Alignment for Domain Adaptation with Pre-trained Inception ResNet

Deep neural networks have been widely used in computer vision. There are several well trained deep neural networks for the ImageNet classification challenge, which has played a significant role in image recognition. However, little work has explored pre-trained neural networks for image recognition in domain adaption. In this paper, we are the first to extract better-represented features from a pre-trained Inception ResNet model for domain adaptation. We then present a modified distribution alignment method for classification using the extracted features. We test our model using three benchmark datasets (Office+Caltech-10, Office-31, and Office-Home). Extensive experiments demonstrate significant improvements (4.8%, 5.5%, and 10%) in classification accuracy over the state-of-the-art.

arXiv:1904.02147

Learning Shared Encoding Representation for End-to-End Speech Recognition Models

In this work, we learn a shared encoding representation for a multi-task neural network model optimized with connectionist temporal classification (CTC) and conventional framewise cross-entropy training criteria. Our experiments show that the multi-task training not only tackles the complexity of optimizing CTC models such as acoustic-to-word but also results in significant improvement compared to the plain-task training with an optimal setup. Furthermore, we propose to use the encoding representation learned by the multi-task network to initialize the encoder of attention-based models. Thereby, we train a deep attention-based end-to-end model with 10 long short-term memory (LSTM) layers of encoder which produces 12.2\% and 22.6\% word-error-rate on Switchboard and CallHome subsets of the Hub5 2000 evaluation.

arXiv:1904.01954

End-to-End Visual Speech Recognition for Small-Scale Datasets

Visual speech recognition models traditionally consist of two stages, feature extraction and classification. Several deep learning approaches have been recently presented aiming to replace the feature extraction stage by automatically extracting features from mouth images. However, research on joint learning of features and classification remains limited. In addition, most of the existing methods require large amounts of data in order to achieve state-of-the-art performance, otherwise they under-perform. In this work, we present an end-to-end visual speech recognition system based on fully-connected layers and Long-Short Memory (LSTM) networks which is suitable for small-scale datasets. The model consists of two streams which extract features directly from the mouth and difference images, respectively. The temporal dynamics in each stream are modelled by a Bidirectional LSTM (BLSTM) and the fusion of the two streams takes place via another BLSTM. An absolute improvement of 0.6%, 3.4%, 3.9%, 11.4% over the state-of-the-art is reported on the OuluVS2, CUAVE, AVLetters and AVLetters2 databases, respectively.

arXiv:1904.01908

Multi-layered Spiking Neural Network with Target Timestamp Threshold Adaptation and STDP

Spiking neural networks (SNNs) are good candidates to produce ultra-energy-efficient hardware. However, the performance of these models is currently behind traditional methods. Introducing multi-layered SNNs is a promising way to reduce this gap. We propose in this paper a new threshold adaptation system which uses a timestamp objective at which neurons should fire. We show that our method leads to state-of-the-art classification rates on the MNIST dataset (98.60%) and the Faces/Motorbikes dataset (99.46%) with an unsupervised SNN followed by a linear SVM. We also investigate the sparsity level of the network by testing different inhibition policies and STDP rules.

arXiv:1904.01893

Semantic Bilinear Pooling for Fine-Grained Recognition

Naturally, fine-grained recognition, e.g., vehicle identification or bird classification, has specific hierarchical labels, where fine categories are always harder to be classified than coarse categories. However, most of the recent deep learning based methods neglect the semantic structure of fine-grained objects and do not take advantage of the traditional fine-grained recognition techniques (e.g. coarse-to-fine classification). In this paper, we propose a novel framework with a two-branch network (coarse branch and fine branch), i.e., semantic bilinear pooling, for fine-grained recognition with a hierarchical label tree. This framework can adaptively learn the semantic information from the hierarchical levels. Specifically, we design a generalized cross-entropy loss for the training of the proposed framework to fully exploit the semantic priors via considering the relevance between adjacent levels and enlarge the distance between samples of different coarse classes. Furthermore, our method leverages only the fine branch when testing so that it adds no overhead to the testing time. Experimental results show that our proposed method achieves state-of-the-art performance on four public datasets.

arXiv:1904.01866공식 코드 · Papers with Code

A Comprehensive Overhaul of Feature Distillation

We investigate the design aspects of feature distillation methods achieving network compression and propose a novel feature distillation method in which the distillation loss is designed to make a synergy among various aspects: teacher transform, student transform, distillation feature position and distance function. Our proposed distillation loss includes a feature transform with a newly designed margin ReLU, a new distillation feature position, and a partial L2 distance function to skip redundant information giving adverse effects to the compression of student. In ImageNet, our proposed method achieves 21.65% of top-1 error with ResNet50, which outperforms the performance of the teacher network, ResNet152. Our proposed method is evaluated on various tasks such as image classification, object detection and semantic segmentation and achieves a significant performance improvement in all tasks. The code is available at https://sites.google.com/view/byeongho-heo/overhaul

arXiv:1904.01766

VideoBERT: A Joint Model for Video and Language Representation Learning

Self-supervised learning has become increasingly important to leverage the abundance of unlabeled data available on platforms like YouTube. Whereas most existing approaches learn low-level representations, we propose a joint visual-linguistic model to learn high-level features without any explicit supervision. In particular, inspired by its recent success in language modeling, we build upon the BERT model to learn bidirectional joint distributions over sequences of visual and linguistic tokens, derived from vector quantization of video data and off-the-shelf speech recognition outputs, respectively. We use VideoBERT in numerous tasks, including action classification and video captioning. We show that it can be applied directly to open-vocabulary classification, and confirm that large amounts of training data and cross-modal information are critical to performance. Furthermore, we outperform the state-of-the-art on video captioning, and quantitative results verify that the model learns high-level semantic features.

arXiv:1904.01723

Empirical Study of Deep Learning for Text Classification in Legal Document Review

Predictive coding has been widely used in legal matters to find relevant or privileged documents in large sets of electronically stored information. It saves the time and cost significantly. Logistic Regression (LR) and Support Vector Machines (SVM) are two popular machine learning algorithms used in predictive coding. Recently, deep learning received a lot of attentions in many industries. This paper reports our preliminary studies in using deep learning in legal document review. Specifically, we conducted experiments to compare deep learning results with results obtained using a SVM algorithm on the four datasets of real legal matters. Our results showed that CNN performed better with larger volume of training dataset and should be a fit method in the text classification in legal industry.

arXiv:1904.01721

Explainable Text Classification in Legal Document Review A Case Study of Explainable Predictive Coding

In today's legal environment, lawsuits and regulatory investigations require companies to embark upon increasingly intensive data-focused engagements to identify, collect and analyze large quantities of data. When documents are staged for review the process can require companies to dedicate an extraordinary level of resources, both with respect to human resources, but also with respect to the use of technology-based techniques to intelligently sift through data. For several years, attorneys have been using a variety of tools to conduct this exercise, and most recently, they are accepting the use of machine learning techniques like text classification to efficiently cull massive volumes of data to identify responsive documents for use in these matters. In recent years, a group of AI and Machine Learning researchers have been actively researching Explainable AI. In an explainable AI system, actions or decisions are human understandable. In typical legal `document review' scenarios, a document can be identified as responsive, as long as one or more of the text snippets in a document are deemed responsive. In these scenarios, if predictive coding can be used to locate these responsive snippets, then attorneys could easily evaluate the model's document classification decision. When deployed with defined and explainable results, predictive coding can drastically enhance the overall quality and speed of the document review process by reducing the time it takes to review documents. The authors of this paper propose the concept of explainable predictive coding and simple explainable predictive coding methods to locate responsive snippets within responsive documents. We also report our preliminary experimental results using the data from an actual legal matter that entailed this type of document review.

arXiv:1904.01608공식 코드 · Papers with Code

Structural Scaffolds for Citation Intent Classification in Scientific Publications

Identifying the intent of a citation in scientific papers (e.g., background information, use of methods, comparing results) is critical for machine reading of individual publications and automated analysis of the scientific literature. We propose structural scaffolds, a multitask model to incorporate structural information of scientific papers into citations for effective classification of citation intents. Our model achieves a new state-of-the-art on an existing ACL anthology dataset (ACL-ARC) with a 13.3% absolute increase in F1 score, without relying on external linguistic resources or hand-engineered features as done in existing methods. In addition, we introduce a new dataset of citation intents (SciCite) which is more than five times larger and covers multiple scientific domains compared with existing datasets. Our code and data are available at: https://github.com/allenai/scicite.

arXiv:1904.01543공식 코드 · Papers with Code

Weisfeiler and Leman go sparse: Towards scalable higher-order graph embeddings

Graph kernels based on the $1$-dimensional Weisfeiler-Leman algorithm and corresponding neural architectures recently emerged as powerful tools for (supervised) learning with graphs. However, due to the purely local nature of the algorithms, they might miss essential patterns in the given data and can only handle binary relations. The $k$-dimensional Weisfeiler-Leman algorithm addresses this by considering $k$-tuples, defined over the set of vertices, and defines a suitable notion of adjacency between these vertex tuples. Hence, it accounts for the higher-order interactions between vertices. However, it does not scale and may suffer from overfitting when used in a machine learning setting. Hence, it remains an important open problem to design WL-based graph learning methods that are simultaneously expressive, scalable, and non-overfitting. Here, we propose local variants and corresponding neural architectures, which consider a subset of the original neighborhood, making them more scalable, and less prone to overfitting. The expressive power of (one of) our algorithms is strictly higher than the original algorithm, in terms of ability to distinguish non-isomorphic graphs. Our experimental study confirms that the local algorithms, both kernel and neural architectures, lead to vastly reduced computation times, and prevent overfitting. The kernel version establishes a new state-of-the-art for graph classification on a wide range of benchmark datasets, while the neural version shows promising performance on large-scale molecular regression tasks.

arXiv:1904.02122

Group-wise classification approach to improve Android malicious apps detection accuracy

In the fast-growing smart devices, Android is the most popular OS, and due to its attractive features, mobility, ease of use, these devices hold sensitive information such as personal data, browsing history, shopping history, financial details, etc. Therefore, any security gap in these devices means that the information stored or accessing the smart devices are at high risk of being breached by the malware. These malware are continuously growing and are also used for military espionage, disrupting the industry, power grids, etc. To detect these malware, traditional signature matching techniques are widely used. However, such strategies are not capable to detect the advanced Android malicious apps because malware developer uses several obfuscation techniques. Hence, researchers are continuously addressing the security issues in the Android based smart devices. Therefore, in this paper using Drebin benchmark malware dataset we experimentally demonstrate how to improve the detection accuracy by analyzing the apps after grouping the collected data based on the permissions and achieved 97.15% overall average accuracy. Our results outperform the accuracy obtained without grouping data (79.27%, 2017), Arp, et al. (94%, 2014), Annamalai et al. (84.29%, 2016), Bahman Rashidi et al. (82%, 2017)) and Ali Feizollah, et al. (95.5%, 2017). The analysis also shows that among the groups, Microphone group detection accuracy is least while Calendar group apps are detected with the highest accuracy, and with the highest accuracy, and for the best performance, one shall take 80-100 features.

arXiv:1904.02092

Interpretable Deep Learning for Two-Prong Jet Classification with Jet Spectra

Classification of jets with deep learning has gained significant attention in recent times. However, the performance of deep neural networks is often achieved at the cost of interpretability. Here we propose an interpretable network trained on the jet spectrum $S_{2}(R)$ which is a two-point correlation function of the jet constituents. The spectrum can be derived from a functional Taylor series of an arbitrary jet classifier function of energy flows. An interpretable network can be obtained by truncating the series. The intermediate feature of the network is an infrared and collinear safe C-correlator which allows us to estimate the importance of a $S_{2}(R)$ deposit at an angular scale R in the classification. The performance of the architecture is comparable to that of a convolutional neural network (CNN) trained on jet images, although the number of inputs and complexity of architecture is significantly simpler than the CNN classifier. We consider two examples: one is the classification of two-prong jets which differ in color charge of the mother particle, and the other is a comparison between Pythia 8 and Herwig 7 generated jets.

arXiv:1904.01987

Hybrid Cosine Based Convolutional Neural Networks

Convolutional neural networks (CNNs) have demonstrated their capability to solve different kind of problems in a very huge number of applications. However, CNNs are limited for their computational and storage requirements. These limitations make difficult to implement these kind of neural networks on embedded devices such as mobile phones, smart cameras or advanced driving assistance systems. In this paper, we present a novel layer named Hybrid Cosine Based Convolution that replaces standard convolutional layers using cosine basis to generate filter weights. The proposed layers provide several advantages: faster convergence in training, the receptive field can be increased at no cost and substantially reduce the number of parameters. We evaluate our proposed layers on three competitive classification tasks where our proposed layers can achieve similar (and in some cases better) performances than VGG and ResNet architectures.

arXiv:1904.01962공식 코드 · Papers with Code

Rep the Set: Neural Networks for Learning Set Representations

In several domains, data objects can be decomposed into sets of simpler objects. It is then natural to represent each object as the set of its components or parts. Many conventional machine learning algorithms are unable to process this kind of representations, since sets may vary in cardinality and elements lack a meaningful ordering. In this paper, we present a new neural network architecture, called RepSet, that can handle examples that are represented as sets of vectors. The proposed model computes the correspondences between an input set and some hidden sets by solving a series of network flow problems. This representation is then fed to a standard neural network architecture to produce the output. The architecture allows end-to-end gradient-based learning. We demonstrate RepSet on classification tasks, including text categorization, and graph classification, and we show that the proposed neural network achieves performance better or comparable to state-of-the-art algorithms.